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

    Neuronpedia

    INDEX
    Explanations

    checkm8 exploit and value statistics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tól
    0.46
     interstitials
    0.46
     subsequ
    0.45
    陬
    0.45
     Isabelle
    0.44
     comulti
    0.44
     доби
    0.44
     Sequel
    0.43
     anu
    0.43
     transatlantic
    0.43
    POSITIVE LOGITS
    get
    0.57
    '
    0.52
    input
    0.49
    0.48
    schw
    0.48
     getIntent
    0.46
    sch
    0.46
    GA
    0.46
    l
    0.46
    jde
    0.46
    Act Density 0.000%

    No Known Activations