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

    Neuronpedia

    INDEX
    Explanations

    Symbol

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    管理员
    -0.06
    Ol
    -0.06
    addElement
    -0.06
     Glen
    -0.06
     caucus
    -0.06
    ckett
    -0.06
    Ber
    -0.06
    353
    -0.05
    'O
    -0.05
    >');↵
    -0.05
    POSITIVE LOGITS
     form
    0.07
     перш
    0.07
     Partial
    0.07
    대회
    0.06
    COPY
    0.06
    begin
    0.06
    川
    0.06
     FORM
    0.06
     emphasizing
    0.06
    düm
    0.06
    Act Density 0.000%

    No Known Activations