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

    Neuronpedia

    INDEX
    Explanations

    code parameters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     basement
    -0.09
    /FM
    -0.08
    OMET
    -0.08
     обз
    -0.07
    usten
    -0.07
     gau
    -0.07
    תח
    -0.07
     బ్య
    -0.07
    (Component
    -0.07
    PEC
    -0.07
    POSITIVE LOGITS
     sustit
    0.09
     substit
    0.09
     substitution
    0.09
     substitutions
    0.09
    Animating
    0.08
     supplying
    0.08
     factual
    0.08
     selbstverständlich
    0.07
     populate
    0.07
    olate
    0.07
    Act Density 0.003%

    No Known Activations