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

    Neuronpedia

    INDEX
    Explanations

    useful

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Shoulder
    -0.07
    110
    -0.07
     candy
    -0.07
     joints
    -0.07
     wagon
    -0.07
    �
    -0.06
     hart
    -0.06
    ณ
    -0.06
    เว
    -0.06
    ISTER
    -0.06
    POSITIVE LOGITS
     dominates
    0.07
    是否
    0.07
     ************************
    0.06
    Ju
    0.06
     晴
    0.06
    properties
    0.06
    (display
    0.06
     vais
    0.06
     BAŞ
    0.06
     furious
    0.06
    Act Density 0.113%

    No Known Activations