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

    Neuronpedia

    INDEX
    Explanations

    keystroke capture, malware

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _obj
    -0.08
    'objet
    -0.08
    oproject
    -0.08
    Weekend
    -0.08
    armen
    -0.08
     proyectos
    -0.08
    foundland
    -0.08
    -week
    -0.07
    Predict
    -0.07
     forecast
    -0.07
    POSITIVE LOGITS
     phishing
    0.10
     captcha
    0.09
     harvest
    0.09
     collecting
    0.09
     harvesting
    0.08
     പിട
    0.08
     keyboard
    0.08
    収
    0.08
     secrets
    0.08
     Earnings
    0.08
    Act Density 0.009%

    No Known Activations