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

    Neuronpedia

    INDEX
    Explanations

    Python glob file finding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pattern
    0.46
    excludes
    0.46
    PATTERN
    0.45
    pom
    0.44
    subtract
    0.42
    anud
    0.42
    REGEX
    0.42
    Exclude
    0.41
    uu
    0.40
    SELECTOR
    0.40
    POSITIVE LOGITS
     drivers
    0.41
     ig
    0.41
     trigger
    0.41
     మో
    0.39
     thisTrack
    0.38
     cav
    0.38
     markers
    0.38
     glob
    0.37
     stationed
    0.36
     replay
    0.36
    Act Density 0.000%

    No Known Activations