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

    Neuronpedia

    INDEX
    Explanations

    HTML structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Configure
    0.84
     Accelerator
    0.80
    Manifest
    0.80
    Ob
    0.80
    Betty
    0.76
    Epic
    0.75
    Templ
    0.73
    disable
    0.73
    Dancing
    0.73
     meticul
    0.73
    POSITIVE LOGITS
     pone
    0.95
     Brend
    0.95
     linemen
    0.92
     اسكت
    0.91
    ifient
    0.88
     pese
    0.87
     WUE
    0.86
     renderEncoder
    0.86
     branchNode
    0.86
    ",[(
    0.85
    Act Density 0.001%

    No Known Activations