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

    Neuronpedia

    INDEX
    Explanations

    Underfunded pension plans

    np_max-act · gemini-2.0-flash

    The neuron chiefly detects numeric expressions, especially financial figures and percentages.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Shawn
    -0.07
     "");
↵
    -0.06
    ponential
    -0.06
    artifact
    -0.06
    Rod
    -0.06
    gressive
    -0.06
     gang
    -0.06
    ]";↵
    -0.06
    ;');↵
    -0.06
    บอล
    -0.06
    POSITIVE LOGITS
     accomp
    0.07
     พล
    0.07
    .CreateTable
    0.06
    .DATA
    0.06
    <source
    0.06
    (COLOR
    0.06
    grand
    0.06
    -thirds
    0.06
     Comm
    0.06
     모델
    0.06
    Act Density 0.008%

    No Known Activations