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

    Neuronpedia

    INDEX
    Explanations

    specialize

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	hs
    -0.06
     bounded
    -0.06
     fusion
    -0.06
     Umb
    -0.06
     극
    -0.06
    astic
    -0.06
     sheds
    -0.06
     Ghost
    -0.06
    eut
    -0.05
     tanks
    -0.05
    POSITIVE LOGITS
    直
    0.07
    todo
    0.07
    emplate
    0.07
    _duration
    0.07
     synchronized
    0.07
     فوق
    0.07
     حاضر
    0.07
    登
    0.07
    ait
    0.07
     그리
    0.06
    Act Density 0.010%

    No Known Activations