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

    Neuronpedia

    INDEX
    Explanations

    medical and legal disclaimers related to a drug or product.

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     entry
    -0.58
    TypedDataSet
    -0.58
     pro
    -0.57
     major
    -0.56
     entrance
    -0.54
     par
    -0.54
     otherwise
    -0.54
     Walkover
    -0.53
     tonight
    -0.52
     setting
    -0.51
    POSITIVE LOGITS
    ulitis
    0.64
     démocr
    0.63
     vectorielles
    0.63
     saites
    0.63
     visuales
    0.60
     commerciales
    0.59
     vectoriales
    0.58
     tutkim
    0.57
     anún
    0.56
     cérami
    0.55
    Act Density 18.264%

    No Known Activations