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

    Neuronpedia

    INDEX
    Explanations

    discussing issues

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aimed
    -0.07
    _near
    -0.07
    ерин
    -0.07
    RYPTO
    -0.06
    stp
    -0.06
    [level
    -0.06
     fitted
    -0.06
    .::.::
    -0.06
    (init
    -0.06
     jas
    -0.06
    POSITIVE LOGITS
    YES
    0.06
     например
    0.06
     ###↵
    0.06
     Stud
    0.06
    ût
    0.06
    509
    0.06
    ालन
    0.06
    =yes
    0.06
    ascending
    0.06
    Otherwise
    0.06
    Act Density 0.178%

    No Known Activations