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

    Neuronpedia

    INDEX
    Explanations

    Math equations symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     અપ
    -0.07
     pressing
    -0.07
     horseback
    -0.07
     capitalization
    -0.07
     constructor
    -0.07
     vaše
    -0.07
     zai
    -0.07
    ની
    -0.07
    loading
    -0.06
     sredstva
    -0.06
    POSITIVE LOGITS
    .Unity
    0.08
    hecy
    0.08
    BER
    0.07
    nommen
    0.07
     meget
    0.07
     hea
    0.07
     membawa
    0.07
     slain
    0.07
    081
    0.07
    ाचार
    0.07
    Act Density 0.046%

    No Known Activations