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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     státy
    -0.08
    dialog
    -0.06
    kr
    -0.06
    cooldown
    -0.06
    .Atomic
    -0.06
    .broadcast
    -0.06
    urator
    -0.06
    _TI
    -0.06
     MediaType
    -0.06
     twink
    -0.06
    POSITIVE LOGITS
    [date
    0.06
    -grey
    0.06
     بلغ
    0.06
     plush
    0.06
     conditioned
    0.06
    _ASSOC
    0.06
    :true
    0.06
     neoliberal
    0.06
     pores
    0.06
    人物
    0.06
    Act Density 0.000%

    No Known Activations