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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     título
    -0.08
     CLEAR
    -0.07
    dd
    -0.07
     bisher
    -0.06
     comment
    -0.06
     frase
    -0.06
     نیرو
    -0.06
     Narrow
    -0.06
    nih
    -0.06
    xdd
    -0.06
    POSITIVE LOGITS
    會
    0.07
     robin
    0.07
     ObjectId
    0.07
    .num
    0.07
     radioactive
    0.07
    OFFSET
    0.06
    atoire
    0.06
    ][
    0.06
     �
    0.06
    顺
    0.06
    Act Density 0.026%

    No Known Activations