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

    Neuronpedia

    INDEX
    Explanations

    It is or it was

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    寻求
    0.44
    積極的に
    0.42
    ここでは
    0.39
    策划
    0.38
     लेखक
    0.37
    शीट
    0.37
    DSM
    0.37
     ശ്രമ
    0.37
    こうした
    0.37
    てもら
    0.37
    POSITIVE LOGITS
     imposible
    0.65
     seems
    0.62
     impossible
    0.61
     raining
    0.61
     snowing
    0.58
     évident
    0.56
     rained
    0.55
     might
    0.54
     doesn
    0.54
    impossible
    0.54
    Act Density 0.011%

    No Known Activations