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

    Neuronpedia

    INDEX
    Explanations

    specific

    np_max-act · gemini-2.0-flash

    The neuron activates on words related to personalization or individual‐specific context.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     millennium
    -0.07
    _dimension
    -0.07
    .Focused
    -0.07
    .TextEdit
    -0.07
    sand
    -0.07
    ρθ
    -0.06
    ød
    -0.06
    PointerType
    -0.06
    .sys
    -0.06
     specular
    -0.06
    POSITIVE LOGITS
     Ratio
    0.07
     โ
    0.07
     милли
    0.07
     philosoph
    0.06
     caract
    0.06
    itness
    0.06
    raries
    0.06
     lesser
    0.06
     Pil
    0.06
    ://"
    0.06
    Act Density 0.016%

    No Known Activations