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

    Neuronpedia

    INDEX
    Explanations

    support/help

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _MODEL
    -0.07
     görmek
    -0.06
     Cab
    -0.06
    케이
    -0.06
    _Checked
    -0.06
     datingsider
    -0.06
     говорить
    -0.06
    _Top
    -0.06
    本当に
    -0.06
    @Bean
    -0.06
    POSITIVE LOGITS
    Simply
    0.07
    ¥
    0.07
    Minimal
    0.06
    _RECE
    0.06
    afia
    0.06
    essaging
    0.06
     tph
    0.06
    �
    0.06
    <any
    0.06
    quent
    0.06
    Act Density 0.006%

    No Known Activations