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

    Neuronpedia

    INDEX
    Explanations

    race

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    POSITE
    -0.06
     είχαν
    -0.06
     assh
    -0.06
    udad
    -0.06
    غم
    -0.06
     محمود
    -0.06
    imap
    -0.06
     bounded
    -0.06
    _mk
    -0.06
    ίναι
    -0.06
    POSITIVE LOGITS
     prompted
    0.08
     dependent
    0.07
     depend
    0.07
     常
    0.07
     participating
    0.06
    群
    0.06
    推
    0.06
    $response
    0.06
     criminal
    0.06
     progression
    0.06
    Act Density 0.003%

    No Known Activations