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

    Neuronpedia

    INDEX
    Explanations

    entropy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kate
    -0.07
     algebra
    -0.07
     Classification
    -0.07
     crosses
    -0.07
    ça
    -0.07
     onItemClick
    -0.07
     mij
    -0.07
     QC
    -0.07
    ewolf
    -0.07
     classification
    -0.06
    POSITIVE LOGITS
    _temperature
    0.07
    เทพ
    0.07
     ent
    0.07
     entropy
    0.06
    %!
    0.06
     منط
    0.06
    .Try
    0.06
     trying
    0.06
    音乐
    0.06
    Entropy
    0.06
    Act Density 0.002%

    No Known Activations