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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     casos
    -0.08
    _STARTED
    -0.07
    、な
    -0.06
     tertiary
    -0.06
     구매
    -0.06
    ocaust
    -0.06
     Commun
    -0.06
     nn
    -0.06
    444
    -0.06
     непосред
    -0.06
    POSITIVE LOGITS
     thoughtful
    0.07
     Large
    0.07
    aras
    0.07
    [vi
    0.07
    lescope
    0.07
     venture
    0.07
     scaled
    0.06
     MPL
    0.06
     robes
    0.06
     amount
    0.06
    Act Density 0.003%

    No Known Activations