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

    Neuronpedia

    INDEX
    Explanations

    lighting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lighting
    -1.97
     Lighting
    -1.79
    Lighting
    -1.67
    lighting
    -1.42
     lightning
    -1.38
     lightening
    -1.25
     Lightning
    -1.19
    LIGHTING
    -1.17
    Lightning
    -1.13
     illumination
    -1.11
    POSITIVE LOGITS
    moveToFirst
    0.57
     према
    0.55
     O
    0.50
     voork
    0.47
    .
    0.43
    readInt
    0.43
    oxys
    0.42
     R
    0.41
     int
    0.41
     us
    0.40
    Act Density 1.115%

    No Known Activations