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

    Neuronpedia

    INDEX
    Explanations

    preamble

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     preamble
    -1.31
    Clik
    -0.67
     виправивши
    -0.67
    Preamble
    -0.63
    WireFormatLite
    -0.61
     CrossRef
    -0.60
    esterno
    -0.59
    iprot
    -0.59
    円
    -0.59
    IntoConstraints
    -0.59
    POSITIVE LOGITS
    d
    0.50
    s
    0.49
    amaha
    0.48
     ho
    0.45
    ataka
    0.45
     Lovel
    0.45
    denes
    0.45
    createComponent
    0.45
     Вікі
    0.44
     Trung
    0.43
    Act Density 0.177%

    No Known Activations