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

    Neuronpedia

    INDEX
    Explanations

    alpha

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    рах
    -0.08
     upbeat
    -0.08
     sustitu
    -0.08
     naš
    -0.07
     ersetzen
    -0.07
     substitutions
    -0.07
     sujeto
    -0.07
     regal
    -0.07
    ご
    -0.07
     replacements
    -0.07
    POSITIVE LOGITS
     lush
    0.09
    /general
    0.08
    Intersect
    0.08
    plein
    0.08
     probeert
    0.08
     środ
    0.08
     منع
    0.07
     rul
    0.07
    Department
    0.07
     தனது
    0.07
    Act Density 0.015%

    No Known Activations