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

    Neuronpedia

    INDEX
    Explanations

    code, programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    )(
    -0.07
    (the
    -0.07
     функци
    -0.06
     })
↵
    -0.06
     VARIABLES
    -0.06
    entieth
    -0.06
    Purpose
    -0.06
     indx
    -0.06
     swollen
    -0.06
     giữ
    -0.06
    POSITIVE LOGITS
    节
    0.06
     taught
    0.06
    _LAYOUT
    0.06
     sklad
    0.06
    =false
    0.06
    _missing
    0.06
    (Channel
    0.06
     смер
    0.06
     negativity
    0.06
    олог
    0.06
    Act Density 0.083%

    No Known Activations