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

    Neuronpedia

    INDEX
    Explanations

    mentioning documentation or projects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     простой
    0.45
    単純
    0.45
    Upon
    0.40
    Simple
    0.39
     simple
    0.38
     severely
    0.37
    uson
    0.36
     acquire
    0.36
    simple
    0.36
     undetected
    0.36
    POSITIVE LOGITS
     mention
    1.91
     언급
    1.80
     mentions
    1.73
     mentioning
    1.67
     Mention
    1.64
    Mention
    1.63
    mention
    1.62
     упомина
    1.62
    提及
    1.48
     mencionar
    1.45
    Act Density 0.049%

    No Known Activations