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

    Neuronpedia

    INDEX
    Explanations

    sales or character names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     balcony
    0.40
     ([
    0.38
    writeData
    0.38
    ↵
    0.37
     brinda
    0.37
    ">${
    0.36
    getRepository
    0.36
     will
    0.35
     Provides
    0.35
     proporciona
    0.34
    POSITIVE LOGITS
    ;.
    0.44
     [];
    0.38
     ;$
    0.37
     '';
    0.36
    ;');
    0.36
    ਾਨੂੰ
    0.36
    もっと
    0.35
    }.$
    0.34
    菒
    0.34
    ++;
    0.33
    Act Density 0.001%

    No Known Activations