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

    Neuronpedia

    INDEX
    Explanations

    Miscellaneous text fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     توضی
    -0.06
    _bet
    -0.06
     Horde
    -0.06
    lendirme
    -0.06
     Blockly
    -0.06
    -forward
    -0.06
     irrelevant
    -0.06
     inch
    -0.06
     wink
    -0.06
     perverse
    -0.06
    POSITIVE LOGITS
    typing
    0.07
     asla
    0.06
    aba
    0.06
    isOk
    0.06
     После
    0.06
     треба
    0.06
    ouched
    0.06
    .Deep
    0.06
    ejména
    0.06
     tuy
    0.06
    Act Density 0.020%

    No Known Activations