Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    expressions of love and commitment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Punctuation and conjunctions followed by common words

    np_acts-logits-general · gemini-2.0-flash

    code or programming documentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     agarre
    -0.55
    楔
    -0.53
     hebdomada
    -0.52
    SharedDtor
    -0.52
     phân
    -0.51
    دانشنامهٔ
    -0.50
     credere
    -0.50
    ent
    -0.49
     personales
    -0.49
     épreuve
    -0.48
    POSITIVE LOGITS
    ]}>
    0.67
     незавершена
    0.64
     Reverso
    0.64
    Naissance
    0.62
    AddTagHelper
    0.60
    RequiresApi
    0.58
     становника
    0.56
    TargetException
    0.55
    djangoproject
    0.55
    -------
    0.55
    Act Density 0.032%

    No Known Activations