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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -conscious
    -0.07
    .Bool
    -0.07
    -depend
    -0.07
    ()"↵
    -0.07
     CompletableFuture
    -0.07
     string
    -0.07
     служби
    -0.07
     dealership
    -0.06
    ього
    -0.06
    IL
    -0.06
    POSITIVE LOGITS
     медицин
    0.06
     stabbed
    0.06
    _WIFI
    0.06
    ’un
    0.06
     opsiyon
    0.06
     roaming
    0.06
    <Category
    0.06
     cg
    0.05
     confuse
    0.05
     emotionally
    0.05
    Act Density 0.006%

    No Known Activations