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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    acio
    -0.06
    ょ
    -0.06
    通過
    -0.06
    ्वर
    -0.06
    '(
    -0.06
    .Middle
    -0.06
    "^
    -0.06
     violate
    -0.05
    zap
    -0.05
     mimic
    -0.05
    POSITIVE LOGITS
     ambigu
    0.07
     Service
    0.07
     香
    0.07
     Riders
    0.06
     smartphone
    0.06
    _DOCUMENT
    0.06
     intrinsic
    0.06
     SERVICE
    0.06
     arguably
    0.06
    .IsNull
    0.06
    Act Density 0.031%

    No Known Activations