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

    Neuronpedia

    INDEX
    Explanations

    divides

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     رف
    -0.08
    Having
    -0.07
     것도
    -0.06
     прох
    -0.06
    ulf
    -0.06
     uploaded
    -0.06
    Different
    -0.06
     emot
    -0.06
    _PA
    -0.06
     mau
    -0.06
    POSITIVE LOGITS
     Dominion
    0.07
    Routes
    0.07
    Pear
    0.06
    슈
    0.06
    ij
    0.06
    cellent
    0.06
    veedor
    0.06
    leases
    0.06
    roll
    0.06
    분
    0.06
    Act Density 0.000%

    No Known Activations