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

    Neuronpedia

    INDEX
    Explanations

    words related to opinions and conclusions

    oai_token-act-pair · gemini-2.0-flash

    opinion

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     صوتيه
    -0.65
    __(/*!
    -0.53
     ddelweddau
    -0.52
     itſelf
    -0.52
     ſtate
    -0.51
     surla
    -0.51
    zels
    -0.49
    StateToProps
    -0.48
    ₂)
    -0.48
    DoubleQuotes
    -0.48
    POSITIVE LOGITS
    oredCriteria
    0.63
    Sursa
    0.52
     Grand
    0.50
    glDelete
    0.49
    yntaxException
    0.49
    EDEFAULT
    0.49
    elemField
    0.48
    PRIME
    0.48
    ьаж
    0.48
     خارجية
    0.47
    Act Density 1.303%

    No Known Activations