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

    Neuronpedia

    INDEX
    Explanations

    action and analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ance
    0.96
    forth
    0.93
    oken
    0.83
    ok
    0.77
    oche
    0.76
    good
    0.76
     Boden
    0.73
    ment
    0.73
    hood
    0.72
     Potential
    0.72
    POSITIVE LOGITS
    Analyzing
    1.26
     mercury
    1.24
     분석
    1.22
    Analyze
    1.21
     arginine
    1.20
     analyze
    1.20
     analyzing
    1.20
     analysing
    1.18
     mathbf
    1.18
    CycleOffset
    1.16
    Act Density 0.000%

    No Known Activations