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

    Neuronpedia

    INDEX
    Explanations

    website code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Memorial
    -0.08
    _content
    -0.07
     autobi
    -0.07
    .Multiline
    -0.07
    _FE
    -0.06
    ?><
    -0.06
     emph
    -0.06
     flowed
    -0.06
    -life
    -0.06
     初
    -0.06
    POSITIVE LOGITS
    уск
    0.06
    .k
    0.06
    ...)↵
    0.06
    [,
    0.06
    уч
    0.06
    lock
    0.06
    _VOICE
    0.06
    .drop
    0.06
    =True
    0.06
    701
    0.06
    Act Density 0.003%

    No Known Activations