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

    Neuronpedia

    INDEX
    Explanations

    derivation or similarity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     或
    -0.07
    187
    -0.07
    comm
    -0.07
    189
    -0.06
    ونت
    -0.06
    ھ
    -0.06
    -Al
    -0.06
    ropping
    -0.06
     Epic
    -0.06
     mish
    -0.06
    POSITIVE LOGITS
     logical
    0.07
    %!
    0.07
     (?)
    0.06
     Jean
    0.06
     morals
    0.06
    іль
    0.06
     TRUE
    0.06
    iče
    0.06
    Britain
    0.06
     emlrt
    0.06
    Act Density 0.717%

    No Known Activations