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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hydrogen
    -0.08
    capability
    -0.07
    -prop
    -0.07
    makes
    -0.06
     component
    -0.06
    estring
    -0.06
    ΗΜ
    -0.06
    ENDER
    -0.06
    运
    -0.06
     (`
    -0.06
    POSITIVE LOGITS
     до
    0.07
     nữa
    0.07
     출연
    0.06
     Paula
    0.06
     δυνα
    0.06
     لأ
    0.06
    Cİ
    0.06
     좋
    0.06
     佐
    0.06
     질
    0.06
    Act Density 0.043%

    No Known Activations