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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash

    references to ambiguity and deception in situations.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Creating
    -0.06
    agento
    -0.06
     Gu
    -0.06
    cheap
    -0.06
    Confirmed
    -0.06
     зав
    -0.06
    อนไลน
    -0.06
     cu
    -0.06
     από
    -0.06
     CommonModule
    -0.06
    POSITIVE LOGITS
     getContext
    0.07
    _processor
    0.07
    _css
    0.07
     lock
    0.07
    ечно
    0.06
     sag
    0.06
    �
    0.06
    .Interval
    0.06
    iver
    0.06
    BUTTON
    0.06
    Act Density 0.054%

    No Known Activations