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

    Neuronpedia

    INDEX
    Explanations

    colon or quotation mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    “A
    -0.07
     TU
    -0.06
    "H
    -0.06
    ध
    -0.06
     cg
    -0.06
     qq
    -0.06
     Fallon
    -0.06
     ATK
    -0.06
    १९
    -0.06
    bound
    -0.06
    POSITIVE LOGITS
    .tick
    0.06
     uneven
    0.06
    _MISC
    0.06
    _Stop
    0.06
    .Connect
    0.06
    ，都
    0.06
    är
    0.06
    =max
    0.06
    _TMP
    0.06
    -eye
    0.06
    Act Density 0.003%

    No Known Activations