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

    Neuronpedia

    INDEX
    Explanations

    reputation and its consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    看起来
    0.42
    }=-
    0.41
     presented
    0.39
    看起來
    0.39
     permissions
    0.38
    setHeader
    0.38
     pessimism
    0.38
     pessimistic
    0.38
     creeps
    0.38
    iteiten
    0.38
    POSITIVE LOGITS
     garnered
    0.63
     auprès
    0.61
     boost
    0.54
     accrued
    0.54
     earned
    0.52
    影响力
    0.51
     accru
    0.50
    earned
    0.50
     boosting
    0.50
    among
    0.49
    Act Density 0.033%

    No Known Activations