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

    Neuronpedia

    INDEX
    Explanations

    "go a long way"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dataframe
    -0.07
     suck
    -0.07
     distributions
    -0.06
     distribution
    -0.06
    	gen
    -0.06
    nět
    -0.06
     klas
    -0.06
     segment
    -0.06
     navy
    -0.06
     redevelopment
    -0.06
    POSITIVE LOGITS
    來
    0.07
    腐
    0.06
     roads
    0.06
    \Support
    0.06
    enef
    0.06
    .Ab
    0.06
     �
    0.06
     miracles
    0.06
    ingredients
    0.06
    kový
    0.06
    Act Density 0.013%

    No Known Activations