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

    Neuronpedia

    INDEX
    Explanations

    choices/options

    np_max-act · gemini-2.0-flash

    This neuron responds to the special Q&A formatting markers (e.g. the “### Answer:” and “### Explanation:” delimiters).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .LA
    -0.07
     awaken
    -0.07
     прежде
    -0.06
     ступ
    -0.06
     leisure
    -0.06
     이루
    -0.06
     genau
    -0.06
     component
    -0.06
     biology
    -0.06
     тоді
    -0.06
    POSITIVE LOGITS
    caps
    0.07
    olls
    0.06
    概
    0.06
    ὲ
    0.06
    ']->
    0.06
    로드
    0.06
    _views
    0.06
     ET
    0.06
    ΙΝ
    0.06
    ivr
    0.06
    Act Density 0.005%

    No Known Activations