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

    Neuronpedia

    INDEX
    Explanations

    thereby

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vital
    -0.07
     مص
    -0.06
    Death
    -0.06
     метал
    -0.06
     Broken
    -0.06
    cháze
    -0.06
    Matcher
    -0.06
    ā
    -0.06
    (AP
    -0.06
    τηγορία
    -0.06
    POSITIVE LOGITS
     party
    0.06
    -party
    0.06
    _rev
    0.06
     tableau
    0.06
    -guide
    0.06
    .conn
    0.06
    Tx
    0.06
    _principal
    0.06
    ano
    0.06
    етерб
    0.06
    Act Density 0.000%

    No Known Activations