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

    Neuronpedia

    INDEX
    Explanations

    diseases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     secluded
    -0.07
    セン
    -0.07
     calculator
    -0.07
    工业大学
    -0.07
     savage
    -0.07
     �
    -0.07
    远处
    -0.06
     Campus
    -0.06
    (second
    -0.06
    _ru
    -0.06
    POSITIVE LOGITS
    essoa
    0.08
     Morm
    0.07
     Portions
    0.07
    😈
    0.07
     Dates
    0.07
     Defaults
    0.07
    お
    0.07
    agram
    0.07
    Bone
    0.07
    "net
    0.07
    Act Density 0.053%

    No Known Activations