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

    Neuronpedia

    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash

    This neuron identifies occurrences of the variable “x” in mathematical expressions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ρίας
    -0.07
     inp
    -0.07
    水
    -0.06
    udd
    -0.06
    cakes
    -0.06
    olang
    -0.06
     Berry
    -0.06
     misplaced
    -0.06
    Fault
    -0.06
    Ins
    -0.06
    POSITIVE LOGITS
     обще
    0.06
     dataTable
    0.06
    _mask
    0.06
     enlarge
    0.06
    duto
    0.06
    .Settings
    0.06
     hardness
    0.06
     eax
    0.06
    /content
    0.06
     apex
    0.06
    Act Density 0.017%

    No Known Activations