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

    Neuronpedia

    INDEX
    Explanations

    -to

    np_max-act · gemini-2.0-flash

    This neuron detects technical mentions of “signal-to-noise” ratios.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    rust
    -0.08
     произ
    -0.07
    `\
    -0.07
    decl
    -0.07
     yapmış
    -0.07
    Раз
    -0.07
    После
    -0.06
     prompt
    -0.06
    ريم
    -0.06
     relieved
    -0.06
    POSITIVE LOGITS
     mortgage
    0.08
    osit
    0.07
    (Menu
    0.06
    -с
    0.06
    tenant
    0.06
    elves
    0.06
     dbo
    0.06
     Gain
    0.06
     Diagnosis
    0.06
    _files
    0.06
    Act Density 0.003%

    No Known Activations