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

    Neuronpedia

    INDEX
    Explanations

    Tables

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ly
    -0.07
     ub
    -0.07
     означ
    -0.07
    ('',
    -0.07
    ('.',
    -0.07
     Geek
    -0.07
     Wyoming
    -0.07
     stále
    -0.07
     rambut
    -0.07
     Graham
    -0.07
    POSITIVE LOGITS
    354
    0.08
    81
    0.08
    526
    0.08
     portray
    0.07
    十
    0.07
    ند
    0.07
    antics
    0.07
    フ
    0.07
    حف
    0.07
    ？↵
    0.07
    Act Density 0.001%

    No Known Activations