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

    Neuronpedia

    INDEX
    Explanations

    PUT

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ışık
    -0.07
    hydro
    -0.06
    _mean
    -0.06
     XIII
    -0.06
    (Test
    -0.06
     Flow
    -0.06
     Extr
    -0.06
    Inputs
    -0.06
     třetí
    -0.06
    indrical
    -0.06
    POSITIVE LOGITS
     PUT
    0.07
     importantly
    0.07
     Reached
    0.06
     reclaimed
    0.06
    =((
    0.06
    PUT
    0.06
     darn
    0.06
    .className
    0.06
     devoted
    0.06
    。此
    0.06
    Act Density 0.002%

    No Known Activations