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

    Neuronpedia

    INDEX
    Explanations

    plans

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    how
    -0.07
     inher
    -0.07
    您
    -0.07
    드로
    -0.06
     actress
    -0.06
    ографія
    -0.06
     ราคา
    -0.06
    arro
    -0.06
    ksiyon
    -0.06
    很
    -0.06
    POSITIVE LOGITS
    ,proto
    0.07
    [V
    0.07
    frei
    0.06
     Instances
    0.06
    署
    0.06
     Gluten
    0.06
    _cleanup
    0.06
     filling
    0.06
    umatic
    0.06
    uff
    0.06
    Act Density 0.054%

    No Known Activations