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

    Neuronpedia

    INDEX
    Explanations

    Notable Features, VIN, BPM

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     drugih
    1.70
    lectual
    1.60
     crackers
    1.58
     widest
    1.53
    uria
    1.52
     trate
    1.52
    Tov
    1.51
    uality
    1.50
    astic
    1.50
    áus
    1.49
    POSITIVE LOGITS
    lonitrile
    2.01
    hdad
    1.90
    instell
    1.78
    swing
    1.76
     десять
    1.70
     EditText
    1.70
    MODULE
    1.68
    eight
    1.65
    ₡
    1.65
    صاص
    1.64
    Act Density 0.092%

    No Known Activations