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

    Neuronpedia

    INDEX
    Explanations

    DNA

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    紧紧
    -0.07
    孳
    -0.07
    Porn
    -0.07
    뻑
    -0.07
     ************************************************
    -0.07
    缲
    -0.07
    gne
    -0.07
     توف
    -0.06
    Proposal
    -0.06
    знач
    -0.06
    POSITIVE LOGITS
    _power
    0.07
     risky
    0.06
     genesis
    0.06
    _regularizer
    0.06
    imeter
    0.06
    �
    0.06
    细节
    0.06
    朋友
    0.06
    大众
    0.06
    肌肉
    0.06
    Act Density 0.013%

    No Known Activations