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

    Neuronpedia

    INDEX
    Explanations

    code snippets/technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oline
    -0.08
     bets
    -0.07
    .dismiss
    -0.07
    „A
    -0.07
    _ATOM
    -0.07
    (total
    -0.07
     rue
    -0.07
    Ru
    -0.07
     forbidden
    -0.06
    ordinal
    -0.06
    POSITIVE LOGITS
    ்�
    0.06
     ASM
    0.06
    :params
    0.06
     Fah
    0.06
    후기
    0.06
    !↵↵↵
    0.05
     안전
    0.05
     трен
    0.05
    (big
    0.05
     shipped
    0.05
    Act Density 0.000%

    No Known Activations