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

    Neuronpedia

    INDEX
    Explanations

    Start of sentences/content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     objectMapper
    -0.08
     hinder
    -0.06
     ί
    -0.06
     })↵↵↵
    -0.06
     roadside
    -0.06
     Glouce
    -0.06
     Wochen
    -0.06
     ArgumentError
    -0.06
    ,target
    -0.06
     лише
    -0.06
    POSITIVE LOGITS
    啊啊
    0.06
     captions
    0.06
     reputable
    0.06
    >\<^
    0.06
     voluntarily
    0.06
    +A
    0.06
     tú
    0.06
    istics
    0.06
    犯
    0.06
    asion
    0.06
    Act Density 0.033%

    No Known Activations