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

    Neuronpedia

    INDEX
    Explanations

    wait

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    โค
    -0.06
     하루
    -0.06
     hemorrh
    -0.06
     FINAL
    -0.06
    úng
    -0.06
    問
    -0.06
    ош
    -0.06
     cabel
    -0.06
     söylem
    -0.06
    .help
    -0.06
    POSITIVE LOGITS
    (Group
    0.07
     Grat
    0.07
    .type
    0.07
    _man
    0.06
     Наг
    0.06
    (Register
    0.06
     Müdürlüğü
    0.06
     equally
    0.06
    apGestureRecognizer
    0.06
    mey
    0.06
    Act Density 0.005%

    No Known Activations