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

    Neuronpedia

    INDEX
    Explanations

    math formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     관한
    -0.07
     -->
    -0.07
    expenses
    -0.06
     refute
    -0.06
    .oper
    -0.06
    Proof
    -0.06
    �
    -0.06
     �
    -0.06
     elite
    -0.06
    授
    -0.06
    POSITIVE LOGITS
    DMI
    0.07
    _MULTI
    0.06
     slim
    0.06
     nearing
    0.06
     inters
    0.06
    Mario
    0.06
     unexpected
    0.06
     göl
    0.06
    ;element
    0.06
     inefficient
    0.06
    Act Density 0.008%

    No Known Activations