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

    Neuronpedia

    INDEX
    Explanations

    Feynman, Fremont, frey

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SCO
    -0.77
    lète
    -0.75
    OpCode
    -0.71
     tùy
    -0.71
    ^\
    -0.70
    irst
    -0.70
    UseVisualStyle
    -0.70
    telt
    -0.70
     Meer
    -0.69
     Referenzen
    -0.69
    POSITIVE LOGITS
     Feynman
    0.89
     Fey
    0.88
    fey
    0.82
     Leighton
    0.78
    absorb
    0.74
    eynman
    0.72
    dimethy
    0.71
     absorbs
    0.70
    diagram
    0.68
     diagrams
    0.67
    Act Density 0.022%

    No Known Activations