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

    Neuronpedia

    INDEX
    Explanations

    true

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Dec
    -0.07
    难得
    -0.07
     Dear
    -0.07
     Those
    -0.07
    越来
    -0.07
     conocer
    -0.07
     dojo
    -0.07
    judul
    -0.07
     helpers
    -0.07
     xứ
    -0.06
    POSITIVE LOGITS
    witter
    0.07
     Armstrong
    0.07
     kết
    0.07
     swim
    0.07
     אותה
    0.07
     harassed
    0.07
     Morse
    0.06
     Apprentice
    0.06
    _commit
    0.06
     Medina
    0.06
    Act Density 0.006%

    No Known Activations