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
    �
    -0.08
    mię
    -0.07
    Trail
    -0.07
    𝕂
    -0.07
    .FontStyle
    -0.07
    _NEW
    -0.06
    翾
    -0.06
     VO
    -0.06
    תיב
    -0.06
    טי
    -0.06
    POSITIVE LOGITS
    자격
    0.08
    ancel
    0.07
     nond
    0.07
     пон
    0.07
    会发生
    0.07
     solves
    0.07
     dict
    0.07
    等待
    0.07
     potent
    0.07
     anticipate
    0.06
    Act Density 0.005%

    No Known Activations