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

    Neuronpedia

    INDEX
    Explanations

    change

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    were
    -0.07
    997
    -0.07
     had
    -0.07
    167
    -0.07
     Prob
    -0.07
     至
    -0.07
     felt
    -0.06
     Wesley
    -0.06
     účet
    -0.06
     Grammy
    -0.06
    POSITIVE LOGITS
     getMenu
    0.07
     '');↵
    0.07
    となり
    0.07
    conf
    0.06
    くな
    0.06
     banning
    0.06
    enuous
    0.06
    .keySet
    0.06
     ');↵
    0.06
    [];↵↵
    0.06
    Act Density 0.292%

    No Known Activations