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

    Neuronpedia

    INDEX
    Explanations

    ®

    np_max-act · gemini-2.0-flash

    The neuron primarily detects numeric quantities and figures (e.g., money amounts, measurements, counts).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Midwest
    -0.07
    acing
    -0.07
    ises
    -0.07
     wide
    -0.06
     woven
    -0.06
     устройства
    -0.06
     thinly
    -0.06
    count
    -0.06
    anno
    -0.06
    АН
    -0.06
    POSITIVE LOGITS
     firstName
    0.07
    -seeking
    0.07
     Felipe
    0.07
    říd
    0.07
     maths
    0.06
    .fs
    0.06
     GUILayout
    0.06
    	Send
    0.06
    Receive
    0.06
    VertexAttribArray
    0.06
    Act Density 0.007%

    No Known Activations