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

    Neuronpedia

    INDEX
    Explanations

    debugging and diagnostics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Partnerships
    0.40
     Señor
    0.39
    Bedroom
    0.39
    createNew
    0.39
     renovación
    0.39
     crear
    0.38
     renewal
    0.38
     believers
    0.38
    راع
    0.38
    renewal
    0.38
    POSITIVE LOGITS
     debugging
    0.88
     debug
    0.82
     Debug
    0.80
     diagnostics
    0.80
     inspect
    0.79
     Diagnostics
    0.76
     diagnose
    0.75
     diagnostic
    0.73
    查看
    0.73
    debug
    0.73
    Act Density 0.384%

    No Known Activations