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

    Neuronpedia

    INDEX
    Explanations

    quotation mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    “A
    -0.06
     liar
    -0.06
    DEL
    -0.06
    �
    -0.06
     rival
    -0.06
    Sat
    -0.06
     activated
    -0.06
    Characters
    -0.06
     mar
    -0.06
    ं
    -0.06
    POSITIVE LOGITS
     innocence
    0.06
    _cr
    0.06
    _SHADER
    0.06
     collaborative
    0.06
    _HELPER
    0.06
     sext
    0.06
    險
    0.06
     bevor
    0.06
    .properties
    0.06
    ιστη
    0.06
    Act Density 0.001%

    No Known Activations