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

    Neuronpedia

    INDEX
    Explanations

    code / math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .instructions
    -0.07
    �
    -0.06
    notEmpty
    -0.06
    ’all
    -0.06
     пом
    -0.06
    ρκε
    -0.06
     đúng
    -0.06
     vešker
    -0.06
    цез
    -0.06
    ozem
    -0.06
    POSITIVE LOGITS
     pricing
    0.08
    ูล
    0.07
     legisl
    0.07
    /V
    0.06
    /H
    0.06
     btn
    0.06
     decreased
    0.06
    hee
    0.06
     suck
    0.06
    esting
    0.06
    Act Density 0.000%

    No Known Activations