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

    Neuronpedia

    INDEX
    Explanations

    ratios

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Amazon
    -0.07
     first
    -0.07
     Worlds
    -0.06
     Tüm
    -0.06
    .Required
    -0.06
    Europe
    -0.06
     spins
    -0.06
    ứng
    -0.06
     spin
    -0.06
     brain
    -0.06
    POSITIVE LOGITS
    ('../../
    0.07
    .');
    0.07
     Apprent
    0.06
    —at
    0.06
    odash
    0.06
     Bucc
    0.06
     рес
    0.06
    _mesh
    0.06
     Irr
    0.06
    —as
    0.06
    Act Density 0.166%

    No Known Activations