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

    Neuronpedia

    INDEX
    Explanations

    patients

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     target
    -1.90
     Target
    -1.80
    Target
    -1.76
    target
    -1.63
     Targets
    -1.52
     targets
    -1.46
     TARGET
    -1.44
    Targets
    -1.37
     cible
    -1.30
    TARGET
    -1.25
    POSITIVE LOGITS
     Siamese
    0.60
     bilinear
    0.58
     desic
    0.56
    ніципа
    0.56
    osocial
    0.54
     blest
    0.54
     trident
    0.54
     Insane
    0.52
    ilden
    0.52
     bluntly
    0.52
    Act Density 0.913%

    No Known Activations