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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     around
    -0.06
    eczy
    -0.06
     Complexity
    -0.06
    .FormBorderStyle
    -0.06
     Beng
    -0.06
    ouve
    -0.06
    +f
    -0.06
     enthusiast
    -0.06
     banking
    -0.06
    íně
    -0.06
    POSITIVE LOGITS
     that
    0.08
    ，那
    0.07
    ующий
    0.07
     disclosing
    0.06
    .visible
    0.06
    statements
    0.06
    жения
    0.06
     Assuming
    0.06
    liest
    0.06
     название
    0.06
    Act Density 0.121%

    No Known Activations