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

    Neuronpedia

    INDEX
    Explanations

    when processing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    "],"
    0.40
    쐞
    0.40
     synthèse
    0.40
     attention
    0.39
     внимание
    0.39
     buildTypes
    0.39
     αφού
    0.38
     jab
    0.38
    ल्याण
    0.38
     bustle
    0.38
    POSITIVE LOGITS
    Possible
    0.42
    可能
    0.41
    Again
    0.39
    あれば
    0.39
    Camping
    0.38
    Somos
    0.38
     deciding
    0.37
    ACP
    0.37
    Dec
    0.37
     Relig
    0.37
    Act Density 0.000%

    No Known Activations