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

    Neuronpedia

    INDEX
    Explanations

    sin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zach
    -0.07
     cracks
    -0.06
    udiant
    -0.06
    trained
    -0.06
    áhnout
    -0.06
     potřeb
    -0.06
    Fant
    -0.06
    Goal
    -0.06
    bullet
    -0.06
     yasal
    -0.06
    POSITIVE LOGITS
     Güney
    0.08
     sinful
    0.07
    inions
    0.07
    忠
    0.07
    ADB
    0.07
     GENERAL
    0.07
    ESC
    0.07
    ulty
    0.07
    AB
    0.07
    asury
    0.07
    Act Density 0.005%

    No Known Activations