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

    Neuronpedia

    INDEX
    Explanations

    atomic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Denise
    -0.07
    縮
    -0.07
    kání
    -0.06
    ’n
    -0.06
     Excel
    -0.06
    zn
    -0.06
    ведите
    -0.06
    ji
    -0.06
     zk
    -0.06
     Thumbnails
    -0.06
    POSITIVE LOGITS
    anio
    0.06
     reinforcing
    0.06
     अ
    0.06
    arias
    0.06
    bach
    0.06
    ังส
    0.06
    -under
    0.06
    移到
    0.06
    烦
    0.06
    stras
    0.06
    Act Density 0.001%

    No Known Activations