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

    Neuronpedia

    INDEX
    Explanations

    mal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     monsters
    -0.08
    ategy
    -0.07
    ICT
    -0.07
     bez
    -0.06
     올라
    -0.06
    _sdk
    -0.06
     вір
    -0.06
    وره
    -0.06
     дит
    -0.06
    498
    -0.06
    POSITIVE LOGITS
    mal
    0.07
    ermal
    0.07
    _SAMPLES
    0.07
     prominently
    0.06
     langs
    0.06
    chal
    0.06
     Paolo
    0.06
     vivastreet
    0.06
    SelfPermission
    0.06
     emailing
    0.06
    Act Density 0.002%

    No Known Activations