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

    Neuronpedia

    INDEX
    Explanations

    disconnection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     yacc
    -0.07
     일
    -0.07
     cần
    -0.06
    _GenericClass
    -0.06
     ArrayCollection
    -0.06
    .prepend
    -0.06
     Oyun
    -0.06
     κατά
    -0.06
     Ryan
    -0.06
    相
    -0.06
    POSITIVE LOGITS
    О
    0.07
    VO
    0.06
     Woj
    0.06
     trough
    0.06
    __,__
    0.06
    -Bar
    0.06
    allow
    0.06
     impressive
    0.06
    .success
    0.06
     hurry
    0.06
    Act Density 0.001%

    No Known Activations