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

    Neuronpedia

    INDEX
    Explanations

    Technical/Academic Writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zi
    -0.07
    єш
    -0.07
    ・ア
    -0.06
     expl
    -0.06
     calm
    -0.06
    olar
    -0.06
    indrical
    -0.06
    ۱۰
    -0.06
     Kar
    -0.06
     NAS
    -0.06
    POSITIVE LOGITS
     reloadData
    0.07
     porte
    0.07
    enumerator
    0.06
     Vec
    0.06
    Segment
    0.06
    311
    0.06
    Vector
    0.06
    și
    0.06
     loading
    0.06
    vertices
    0.06
    Act Density 0.000%

    No Known Activations