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

    Neuronpedia

    INDEX
    Explanations

    color

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    쨈
    -0.07
    bagai
    -0.07
    frog
    -0.07
    군
    -0.07
    敗
    -0.07
     Fishing
    -0.07
    组
    -0.07
    ᠨ
    -0.07
    فق
    -0.07
    чит
    -0.06
    POSITIVE LOGITS
    ותו
    0.06
    });
↵
↵
    0.06
     TP
    0.06
    博士学位
    0.06
    (decimal
    0.06
    (wx
    0.06
    igne
    0.06
    ));↵↵↵
    0.06
    ();
↵
↵
    0.06
    '");↵
    0.06
    Act Density 0.002%

    No Known Activations