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

    Neuronpedia

    INDEX
    Explanations

    SPECIAL

    np_max-act · gemini-2.0-flash

    The neuron fires on the “special/indirect/consequential damages” terms commonly found in software‐license warranty disclaimers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    *p
    -0.07
    스토
    -0.07
    Stars
    -0.07
     corrupt
    -0.07
    _Thread
    -0.06
    ース
    -0.06
     ftp
    -0.06
    direct
    -0.06
     Damon
    -0.06
    全部
    -0.06
    POSITIVE LOGITS
    _MAC
    0.07
    .setFill
    0.07
    obic
    0.06
     phenomena
    0.06
     öner
    0.06
     temiz
    0.06
     Toggle
    0.06
     exceptions
    0.06
    111
    0.06
    .Toggle
    0.06
    Act Density 0.001%

    No Known Activations