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

    Neuronpedia

    INDEX
    Explanations

    File

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Benef
    -0.08
     עצמו
    -0.07
    fern
    -0.07
     дерев
    -0.07
    detach
    -0.07
    SYSTEM
    -0.07
     하나
    -0.07
    ентр
    -0.07
     Centro
    -0.07
    cross
    -0.07
    POSITIVE LOGITS
    までの
    0.08
     />)↵
    0.07
    /manage
    0.07
     vk
    0.07
    "]=="
    0.07
    registr
    0.07
    _mk
    0.07
     pills
    0.07
     sitcom
    0.07
    lük
    0.07
    Act Density 0.001%

    No Known Activations