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

    Neuronpedia

    INDEX
    Explanations

    divisibility checks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     roast
    -0.07
    _handling
    -0.07
    compile
    -0.06
    ]:↵↵↵
    -0.06
     lodge
    -0.06
     씨
    -0.06
     dads
    -0.06
    ��
    -0.06
    REW
    -0.06
    _votes
    -0.06
    POSITIVE LOGITS
    .packet
    0.07
     elev
    0.06
     really
    0.06
     objekt
    0.06
     parade
    0.06
    Austin
    0.06
     pocit
    0.06
     музы
    0.06
    カテゴリ
    0.06
     označ
    0.06
    Act Density 0.016%

    No Known Activations