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

    Neuronpedia

    INDEX
    Explanations

    Self

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ed
    -0.73
    em
    -0.60
    ats
    -0.59
    able
    -0.55
    azione
    -0.54
    oom
    -0.54
    oto
    -0.50
    Self
    -0.49
     dead
    -0.49
    ap
    -0.49
    POSITIVE LOGITS
    //
    0.80
     frattempo
    0.69
    DockStyle
    0.68
     tartalomajánló
    0.68
    AddHtmlAttribute
    0.67
     mesmos
    0.64
     engraçadas
    0.63
     étroite
    0.61
    #
    0.61
    UrlResolution
    0.61
    Act Density 0.251%

    No Known Activations