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

    Neuronpedia

    INDEX
    Explanations

    .assertFalse

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cage
    -0.07
     اصل
    -0.06
    Bean
    -0.06
    boxing
    -0.06
     predicates
    -0.06
    Mixed
    -0.06
     lehet
    -0.06
    _WARNING
    -0.06
     caus
    -0.06
    老师
    -0.06
    POSITIVE LOGITS
    art
    0.07
    (Tag
    0.06
    _INIT
    0.06
    沒
    0.06
     Alleg
    0.06
    $db
    0.06
    went
    0.06
    户
    0.06
    agree
    0.06
    criptor
    0.06
    Act Density 0.000%

    No Known Activations