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

    Neuronpedia

    INDEX
    Explanations

    car models

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.60
     createState
    -0.53
    chọn
    -0.49
     TextInputType
    -0.47
    TacToe
    -0.46
     Uni
    -0.46
     combs
    -0.46
     Oedipus
    -0.46
    uteurs
    -0.46
    Carriera
    -0.46
    POSITIVE LOGITS
    :✨
    0.65
    IsContent
    0.64
    WebVitals
    0.60
     nakalista
    0.57
    WaitGroup
    0.55
    +:+
    0.55
    ConstraintMaker
    0.55
    يميديا
    0.53
    eqn
    0.52
    richTextPanel
    0.52
    Act Density 0.001%

    No Known Activations