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

    Neuronpedia

    INDEX
    Explanations

    Returns

    np_max-act · gemini-2.0-flash

    The neuron fires on floating-point numeric literals (numbers with a decimal point) embedded in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     hateful
    -0.07
    ;:;:;:;:
    -0.07
    टन
    -0.06
    íř
    -0.06
     ApplicationUser
    -0.06
    .bpm
    -0.06
    الیا
    -0.06
    idae
    -0.06
    -associated
    -0.06
     За
    -0.06
    POSITIVE LOGITS
    Loss
    0.07
     Bahrain
    0.07
     investment
    0.06
     impr
    0.06
    nilai
    0.06
    ]];↵
    0.06
    "])↵↵
    0.06
    "path
    0.06
    MASK
    0.06
    لیس
    0.06
    Act Density 0.010%

    No Known Activations