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

    Neuronpedia

    INDEX
    Explanations

    references to time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    \P
    -0.07
    _imag
    -0.07
    )t
    -0.06
     weigh
    -0.06
    them
    -0.06
     nás
    -0.06
    ==========↵
    -0.06
    	as
    -0.06
     urn
    -0.06
     {},
    -0.06
    POSITIVE LOGITS
    _MOUNT
    0.06
     çık
    0.06
     shampoo
    0.06
    権
    0.06
     gleich
    0.06
     writeFile
    0.06
    keeping
    0.06
     �
    0.06
     keş
    0.06
     výbě
    0.06
    Act Density 0.007%

    No Known Activations