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

    Neuronpedia

    INDEX
    Explanations

    colons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ності
    -0.07
    *I
    -0.07
     barn
    -0.06
    ’i
    -0.06
     своїх
    -0.06
     sólo
    -0.06
     thinkers
    -0.06
     WANT
    -0.06
     tarde
    -0.06
     tricks
    -0.06
    POSITIVE LOGITS
    асти
    0.07
    _FWD
    0.06
    exter
    0.06
    [...,
    0.06
    채
    0.06
    Elect
    0.06
     इल
    0.06
     carrier
    0.06
    관리자
    0.06
    ','=','
    0.06
    Act Density 0.001%

    No Known Activations