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

    Neuronpedia

    INDEX
    Explanations

    here

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    erequisites
    -0.07
    PrimaryKey
    -0.06
    .Unlock
    -0.06
    .AddModelError
    -0.06
    ,…↵↵
    -0.06
     па
    -0.06
    _gap
    -0.06
    징
    -0.06
    .sigma
    -0.06
    uç
    -0.06
    POSITIVE LOGITS
    /list
    0.07
     regarded
    0.06
     configurable
    0.06
    _locale
    0.06
    emperature
    0.06
    inv
    0.06
     verschied
    0.06
     villages
    0.06
    doctrine
    0.06
     pearls
    0.06
    Act Density 0.006%

    No Known Activations