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

    Neuronpedia

    INDEX
    Explanations

    down

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    尋
    -0.08
    thé
    -0.08
    "c
    -0.07
    ating
    -0.07
     хоч
    -0.07
     motivating
    -0.07
     الاست
    -0.07
    .Head
    -0.07
     guitarist
    -0.06
    .setContentType
    -0.06
    POSITIVE LOGITS
    平整
    0.07
     Registro
    0.07
     Rock
    0.07
     enough
    0.07
     Weld
    0.07
    义乌
    0.06
     Ms
    0.06
    难怪
    0.06
     Everett
    0.06
     endian
    0.06
    Act Density 0.020%

    No Known Activations