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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lynch
    -0.07
     daha
    -0.07
     apar
    -0.07
     quale
    -0.07
     NotFound
    -0.07
     như
    -0.07
     anche
    -0.06
    不得
    -0.06
     yên
    -0.06
     naj
    -0.06
    POSITIVE LOGITS
    _SS
    0.08
    aling
    0.07
    	exp
    0.07
    SS
    0.06
    metal
    0.06
     prominently
    0.06
     JO
    0.06
    IALIZ
    0.06
    _xs
    0.06
    itous
    0.06
    Act Density 0.067%

    No Known Activations