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

    Neuronpedia

    INDEX
    Explanations

    request

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cry
    -0.06
     gia
    -0.06
     Burn
    -0.06
    senal
    -0.06
    親
    -0.06
     관
    -0.06
     ":"
    -0.06
     trừ
    -0.06
    eed
    -0.06
    Kids
    -0.06
    POSITIVE LOGITS
     transitioning
    0.07
    ние
    0.06
     hangi
    0.06
    пат
    0.06
     midi
    0.06
    ocities
    0.06
     ASD
    0.06
    ,ll
    0.06
    ,eg
    0.06
     AccessToken
    0.06
    Act Density 0.038%

    No Known Activations