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

    Neuronpedia

    INDEX
    Explanations

    animation/VFX

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SQUARE
    -0.07
     debe
    -0.07
    Ke
    -0.06
     cận
    -0.06
     survivors
    -0.06
     >↵↵
    -0.06
     ou
    -0.06
    .Try
    -0.06
    レス
    -0.06
    ValueCollection
    -0.06
    POSITIVE LOGITS
    ，其中
    0.06
    :none
    0.06
     mails
    0.06
     ArgumentException
    0.06
    ../../../
    0.06
    :function
    0.06
    !_
    0.06
     expr
    0.05
     จำนวน
    0.05
    +n
    0.05
    Act Density 0.045%

    No Known Activations