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

    Neuronpedia

    INDEX
    Explanations

    coding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.06
     Nylon
    -0.06
    Fallback
    -0.06
    (shape
    -0.06
    _slave
    -0.06
     acne
    -0.06
     biç
    -0.06
     precondition
    -0.06
    iể
    -0.06
    �
    -0.05
    POSITIVE LOGITS
    RIGHT
    0.07
     )
↵
    0.07
    Clone
    0.07
    his
    0.07
    -over
    0.06
     Ти
    0.06
                    
    0.06
     LESS
    0.06
     în
    0.06
    -play
    0.06
    Act Density 0.001%

    No Known Activations