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

    Neuronpedia

    INDEX
    Explanations

    code errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Studies
    -0.06
     الكتاب
    -0.06
     prostituer
    -0.06
     isKindOfClass
    -0.06
    transforms
    -0.06
    ired
    -0.06
    _photos
    -0.06
    иш
    -0.06
     Cooke
    -0.06
     النظام
    -0.06
    POSITIVE LOGITS
    том
    0.07
    ITER
    0.07
    tp
    0.07
    URLOPT
    0.07
    ��
    0.07
     hard
    0.06
    =========↵
    0.06
     dem
    0.06
    163
    0.06
     lock
    0.06
    Act Density 0.000%

    No Known Activations