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

    Neuronpedia

    INDEX
    Explanations

    crush

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dare
    -0.07
     geçerli
    -0.07
    gado
    -0.06
    Це
    -0.06
    /time
    -0.06
    (Message
    -0.06
     ціка
    -0.06
     Wil
    -0.06
     bald
    -0.06
    _ready
    -0.06
    POSITIVE LOGITS
     crushed
    0.08
    -upload
    0.08
     Crusher
    0.07
     Crush
    0.07
    Match
    0.07
    ठन
    0.07
    ）。↵
    0.06
     weighing
    0.06
    단
    0.06
     CSP
    0.06
    Act Density 0.018%

    No Known Activations