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

    Neuronpedia

    INDEX
    Explanations

    combining historical data and specifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    كر
    0.44
    FieldNumber
    0.43
    学習
    0.40
     रिपीट
    0.40
     الجديدة
    0.40
    計算
    0.40
    Girls
    0.39
    Direction
    0.38
    ន៍
    0.38
    kent
    0.38
    POSITIVE LOGITS
     diluted
    0.42
     filosofía
    0.41
     jalap
    0.39
     dilat
    0.39
     widened
    0.39
     nerfs
    0.39
    눕
    0.37
     elevados
    0.37
     snacking
    0.36
     avoided
    0.36
    Act Density 0.000%

    No Known Activations