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

    Neuronpedia

    INDEX
    Explanations

    primary future actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    次方
    0.46
    okovic
    0.39
    ショナル
    0.39
    тт
    0.38
     ؛
    0.38
    ടതി
    0.38
    lée
    0.38
     તમને
    0.38
    υγ
    0.38
    必ず
    0.37
    POSITIVE LOGITS
     initially
    0.69
    Initially
    0.67
     primarily
    0.66
     Initially
    0.66
     mainly
    0.66
     principalmente
    0.66
     Primarily
    0.64
     주로
    0.61
     Mainly
    0.60
    primarily
    0.60
    Act Density 0.001%

    No Known Activations