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

    Neuronpedia

    INDEX
    Explanations

    phrases related to education and community engagement

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

    Follows a noun or pronoun

    np_acts-logits-general · gemini-2.0-flash

    self data atmosphere point courage apache IFT

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     „
    -0.56
     “
    -0.49
     však
    -0.49
     (“
    -0.48
    скоре
    -0.48
    需
    -0.48
    イイ
    -0.47
    endrait
    -0.47
     endast
    -0.47
    成的
    -0.46
    POSITIVE LOGITS
     resourceCulture
    0.92
     really
    0.90
    StoreMessageInfo
    0.88
     basically
    0.86
     kind
    0.85
     yeah
    0.83
    +#+#
    0.83
     uh
    0.83
     Yeah
    0.81
    ConstraintMaker
    0.79
    Act Density 0.311%

    No Known Activations