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

    Neuronpedia

    INDEX
    Explanations

    hygiene

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _OBS
    -0.07
    //!
    -0.06
    ας
    -0.06
    �
    -0.06
    pizza
    -0.06
     cake
    -0.06
    :date
    -0.06
    225
    -0.06
    89
    -0.06
    /kubernetes
    -0.06
    POSITIVE LOGITS
     руками
    0.07
    ственное
    0.07
     Hammond
    0.06
    ilda
    0.06
     habitual
    0.06
     Teknik
    0.06
    омен
    0.06
     благод
    0.06
     Viol
    0.06
    _travel
    0.06
    Act Density 0.004%

    No Known Activations