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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash

    The neuron activates on the conjunction “and” connecting parts of mathematical instructions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ेव
    -0.07
    endar
    -0.07
    �
    -0.07
    новаж
    -0.07
     simult
    -0.06
    .translation
    -0.06
    посеред
    -0.06
    .True
    -0.06
     सब
    -0.06
     μέχρι
    -0.06
    POSITIVE LOGITS
    _TRY
    0.06
    _SIGN
    0.06
     《
    0.06
    Hosting
    0.06
    Dual
    0.06
     COLOR
    0.06
    -producing
    0.06
    =start
    0.06
    DSA
    0.06
    (SYS
    0.06
    Act Density 0.001%

    No Known Activations