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

    Neuronpedia

    INDEX
    Explanations

    admit

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of evidence admission, i.e. phrases indicating that something was “admitted into evidence” or similar.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     traction
    -0.06
     preempt
    -0.06
    ДА
    -0.06
     mile
    -0.06
     jt
    -0.06
     poner
    -0.06
     대해
    -0.06
     شده
    -0.06
    -0.06
    ForKey
    -0.06
    POSITIVE LOGITS
    }/${
    0.07
    piel
    0.06
    開始
    0.06
    mad
    0.06
    /${
    0.06
     validating
    0.06
     ruby
    0.06
    ouve
    0.06
     mixes
    0.06
    omination
    0.06
    Act Density 0.002%

    No Known Activations