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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reductions
    -0.08
     waited
    -0.08
     Headers
    -0.07
     основе
    -0.07
     waits
    -0.07
     appet
    -0.07
    FromBody
    -0.07
    іть
    -0.07
    defs
    -0.07
     한국
    -0.07
    POSITIVE LOGITS
     التق
    0.06
     PhoneNumber
    0.06
    _ab
    0.06
    {}'.
    0.06
     Lob
    0.06
     OnTrigger
    0.05
     myfile
    0.05
    inness
    0.05
    .constant
    0.05
    uen
    0.05
    Act Density 0.019%

    No Known Activations