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

    Neuronpedia

    INDEX
    Explanations

    phrases related to loss of rights or economic consequences

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

    after possessive pronouns

    np_acts-logits-general · gemini-2.0-flash

    destroying hopes or credibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cientí
    -0.58
    mmation
    -0.49
    CodedInputStream
    -0.49
     bakgrund
    -0.46
    င်း
    -0.46
     سكانية
    -0.46
     LoggerFactory
    -0.46
     particulières
    -0.46
    bewerken
    -0.45
    bleau
    -0.44
    POSITIVE LOGITS
     hopes
    0.94
    好不容易
    0.84
    AddTagHelper
    0.82
     credibility
    0.79
     hope
    0.76
     hoped
    0.75
    EndInit
    0.73
     cherished
    0.73
     entire
    0.71
     usefulness
    0.71
    Act Density 0.648%

    No Known Activations