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

    Neuronpedia

    INDEX
    Explanations

    self-improvement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     that
    -0.65
     a
    -0.57
     to
    -0.55
     for
    -0.52
     itself
    -0.52
    .
    -0.51
     via
    -0.49
    based
    -0.49
     its
    -0.49
     ideje
    -0.48
    POSITIVE LOGITS
    Tikang
    0.95
    verwijspagina
    0.83
    GHIJKLM
    0.81
     linkovi
    0.79
    ividual
    0.78
    nesses
    0.77
     يتيمه
    0.77
    URLException
    0.77
    "]/
    0.77
    OGND
    0.77
    Act Density 0.213%

    No Known Activations