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

    Neuronpedia

    INDEX
    Explanations

    branding and logos

    np_max-act · gemini-2.0-flash

    The neuron detects references to branding or brand identity (e.g., logos, names, livery, branded).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    458
    -0.07
    華
    -0.06
     Adding
    -0.06
    Зап
    -0.06
     desert
    -0.06
    model
    -0.06
     prefetch
    -0.06
     tree
    -0.06
    еф
    -0.06
    akh
    -0.06
    POSITIVE LOGITS
     contag
    0.07
    _ISR
    0.07
    __(↵
    0.07
     TAS
    0.07
    /problems
    0.06
     consolid
    0.06
    =======
    0.06
    _EXEC
    0.06
     Routing
    0.06
    _OPENGL
    0.06
    Act Density 0.032%

    No Known Activations