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

    Neuronpedia

    INDEX
    Explanations

    photographer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    וחות
    0.41
     Mim
    0.39
     Scheduler
    0.39
     úpl
    0.39
     Waters
    0.38
     RIP
    0.38
     currently
    0.38
     teslim
    0.38
    の設定
    0.37
     Inet
    0.37
    POSITIVE LOGITS
    assung
    0.42
    =>$
    0.41
    import
    0.39
    rotic
    0.39
    order
    0.38
    合法
    0.38
    speaker
    0.37
    ş
    0.37
    issantes
    0.36
    sphinx
    0.36
    Act Density 0.001%

    No Known Activations