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

    Neuronpedia

    INDEX
    Explanations

    mental health resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lazy
    0.38
    肚子
    0.38
    hop
    0.38
     pit
    0.37
     Pit
    0.37
    Pit
    0.37
    od
    0.37
    odb
    0.36
    ods
    0.35
    enio
    0.35
    POSITIVE LOGITS
     मार्ट
    0.42
     martin
    0.41
    Martin
    0.39
     pali
    0.39
     MARTIN
    0.38
     catalysts
    0.37
     پال
    0.37
     паль
    0.37
     Palt
    0.37
     حرم
    0.37
    Act Density 0.010%

    No Known Activations