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

    Neuronpedia

    INDEX
    Explanations

    start of sentences/titles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _velocity
    -0.06
     Horror
    -0.06
     �
    -0.06
    WithEmail
    -0.06
     が
    -0.06
    RTC
    -0.06
    _average
    -0.06
    declar
    -0.06
    距
    -0.06
    ui
    -0.06
    POSITIVE LOGITS
     başar
    0.07
    (Border
    0.07
    �
    0.07
     ASAP
    0.06
    perse
    0.06
    jan
    0.06
     Ser
    0.06
    suppress
    0.06
     Scripts
    0.06
    agements
    0.06
    Act Density 0.006%

    No Known Activations