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

    Neuronpedia

    INDEX
    Explanations

    imp

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     മെഡ
    -0.08
    -0.07
    409
    -0.07
     мист
    -0.07
     би
    -0.07
    Blog
    -0.07
    Near
    -0.07
    igua
    -0.07
    IEEE
    -0.07
    _\
    -0.07
    POSITIVE LOGITS
     Lith
    0.08
    burg
    0.08
    енка
    0.08
     Kaff
    0.08
     początku
    0.08
    ulu
    0.08
     hens
    0.08
     estudantes
    0.08
     izi
    0.08
     lith
    0.08
    Act Density 0.000%
    No Known Activations