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

    Neuronpedia

    INDEX
    Explanations

    features and benefits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lut
    0.49
     Validators
    0.46
     ransomware
    0.45
     Thay
    0.45
     diamant
    0.45
     Rhonda
    0.44
     Concepción
    0.44
     Лон
    0.44
     intoler
    0.44
     arma
    0.44
    POSITIVE LOGITS
    0.46
    муж
    0.43
    ificazione
    0.42
    Parameterized
    0.42
     prosperous
    0.41
    ানের
    0.40
    اشت
    0.40
    얏
    0.39
    government
    0.39
    शिक्षा
    0.39
    Act Density 0.003%

    No Known Activations