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

    Neuronpedia

    INDEX
    Explanations

    service

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    243
    -0.07
    روط
    -0.07
     nejen
    -0.06
    iffs
    -0.06
    �
    -0.06
    افي
    -0.06
     hostname
    -0.06
    (off
    -0.06
     overnight
    -0.06
     Roth
    -0.06
    POSITIVE LOGITS
     sparked
    0.07
    orElse
    0.06
    _exc
    0.06
     entwick
    0.06
    isSelected
    0.06
     uns
    0.06
    -des
    0.06
     eines
    0.06
     baz
    0.06
     ();↵
    0.06
    Act Density 0.011%

    No Known Activations