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

    Neuronpedia

    INDEX
    Explanations

    ian

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _bytes
    -0.07
     английск
    -0.07
     fours
    -0.07
    ⤄
    -0.07
    .arc
    -0.07
    .goBack
    -0.07
    acies
    -0.07
    淡水
    -0.07
    萤
    -0.07
     трав
    -0.06
    POSITIVE LOGITS
    مول
    0.08
    号线
    0.07
     escaped
    0.07
    йт
    0.07
    esto
    0.07
    IDGET
    0.07
    ogle
    0.07
    plugin
    0.07
    dit
    0.07
    ake
    0.06
    Act Density 0.000%

    No Known Activations