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

    Neuronpedia

    INDEX
    Explanations

    ies

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of the logical implication marker “implies” (often rendered via the TeX command `\implies`).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .od
    -0.06
     guidance
    -0.06
    Pane
    -0.06
     Addr
    -0.06
     araştırma
    -0.06
     bě
    -0.06
     fan
    -0.06
    .servlet
    -0.06
     starters
    -0.06
     mùi
    -0.06
    POSITIVE LOGITS
    ære
    0.07
    нул
    0.06
    formData
    0.06
    asInstanceOf
    0.06
     İb
    0.06
    Modal
    0.06
    шей
    0.06
     Vs
    0.06
    tos
    0.06
    ्सर
    0.06
    Act Density 0.006%

    No Known Activations