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

    Neuronpedia

    INDEX
    Explanations

    a sense of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     addCriterion
    -0.11
    //{{
    -0.11
    ÂĢÂĢ
    -0.10
    езÑĥлÑĮÑĤ
    -0.09
    .metro
    -0.09
    Verdana
    -0.09
    <|begin_of_text|>
    -0.09
    EMPLARY
    -0.09
     kaldır
    -0.09
     kurtar
    -0.08
    POSITIVE LOGITS
    693
    0.09
    _DEPRECATED
    0.08
     ::
    0.08
    _/
    0.07
     regardless
    0.07
    -ok
    0.07
    @@
    0.07
    _
    0.07
    558
    0.07
     emerg
    0.07
    Act Density 0.172%

    No Known Activations