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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    linked
    -0.07
     discrepan
    -0.06
    Ϲ
    -0.06
    oshi
    -0.06
     sublic
    -0.06
     complicated
    -0.06
    ώ
    -0.06
    formed
    -0.06
    新三
    -0.06
    xdf
    -0.06
    POSITIVE LOGITS
     PA
    0.07
     Jacqu
    0.07
    _IRQ
    0.07
     نها
    0.07
    Hell
    0.06
    ％
    0.06
     hero
    0.06
     наз
    0.06
    每个
    0.06
     liệu
    0.06
    Act Density 0.010%

    No Known Activations