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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash

    This neuron detects numeric ranges or word‐count markers (numbers followed by a hyphen).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     понять
    -0.07
     přičemž
    -0.07
    ってい
    -0.06
     zo
    -0.06
    ану
    -0.06
    graphic
    -0.06
    trap
    -0.06
    	bl
    -0.06
     яка
    -0.06
     clone
    -0.06
    POSITIVE LOGITS
    CCI
    0.07
    <Block
    0.06
     condemned
    0.06
     JFK
    0.06
    苗
    0.06
    Response
    0.06
    .News
    0.06
    lama
    0.06
    .Items
    0.06
    Channels
    0.06
    Act Density 0.001%

    No Known Activations