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

    Neuronpedia

    INDEX
    Explanations

    python, javascript, sql code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     denaturation
    0.45
     pollutants
    0.39
     dyes
    0.39
     cancerous
    0.38
     virulent
    0.38
     pesticides
    0.37
     bleaching
    0.37
     pesticide
    0.37
     odors
    0.36
     liabilities
    0.36
    POSITIVE LOGITS
    k
    0.49
    ко
    0.48
    ת
    0.46
    a
    0.43
    ك
    0.43
    ud
    0.41
    in
    0.40
    it
    0.40
    द
    0.40
    т
    0.39
    Act Density 0.085%

    No Known Activations