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

    Neuronpedia

    INDEX
    Explanations

    =" or "

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Vous
    -0.07
     Все
    -0.07
     tangent
    -0.07
     handleClick
    -0.07
     assert
    -0.07
    答
    -0.07
    깔
    -0.06
    Ins
    -0.06
    /posts
    -0.06
    (False
    -0.06
    POSITIVE LOGITS
    后备
    0.07
     Nano
    0.07
     dairy
    0.07
    毂
    0.07
     girlfriends
    0.07
    Unsupported
    0.07
    Invocation
    0.07
     Paolo
    0.07
    入围
    0.06
    갤
    0.06
    Act Density 0.011%

    No Known Activations