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

    Neuronpedia

    INDEX
    Explanations

    its

    np_max-act · gemini-2.0-flash

    Explanation of neuron 4 behavior: the main thing this neuron does is find words related to selling transactions (forms of “sell,” “sale,” “sells,” “selling,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    روش
    -0.07
     cycles
    -0.06
    .Theme
    -0.06
    婷
    -0.06
    Destructor
    -0.06
    ＿＿＿＿＿＿＿＿
    -0.06
     채용
    -0.06
    북도
    -0.06
    DG
    -0.06
    áh
    -0.06
    POSITIVE LOGITS
     breadth
    0.06
     Geography
    0.06
    \Array
    0.06
    songs
    0.06
     Strand
    0.06
    باب
    0.06
    bou
    0.06
    -ad
    0.06
    ...↵↵
    0.06
    /prom
    0.06
    Act Density 0.014%

    No Known Activations