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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    %.↵↵
    -0.07
    EXIST
    -0.07
    بالإنجليزية
    -0.07
     přist
    -0.07
    _PRINT
    -0.07
     UNITY
    -0.06
    .'_
    -0.06
     باع
    -0.06
     pokud
    -0.06
    _$
    -0.06
    POSITIVE LOGITS
    otty
    0.07
     dys
    0.06
     leather
    0.06
     fence
    0.06
     ship
    0.06
    -bel
    0.06
    ren
    0.06
    asının
    0.06
    andles
    0.06
     iv
    0.06
    Act Density 0.007%

    No Known Activations