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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    achment
    -0.06
    ét
    -0.06
     censor
    -0.06
    .tv
    -0.06
    Ố
    -0.06
    .bl
    -0.06
     мор
    -0.06
     спів
    -0.06
    νει
    -0.06
    Uno
    -0.06
    POSITIVE LOGITS
     Rehabilitation
    0.07
    _secure
    0.07
     λίγ
    0.06
    _TIMES
    0.06
     csr
    0.06
    这样
    0.06
    ～↵↵
    0.06
    :'↵
    0.06
     today
    0.06
     amount
    0.06
    Act Density 0.015%

    No Known Activations