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

    Neuronpedia

    INDEX
    Explanations

    lesson

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     decline
    -0.06
    boost
    -0.06
    िकल
    -0.06
    hosts
    -0.06
    okens
    -0.06
     cihaz
    -0.06
     chồng
    -0.06
    -reg
    -0.06
    .Host
    -0.06
     destination
    -0.05
    POSITIVE LOGITS
    ardin
    0.08
     verk
    0.07
     Vol
    0.07
     utilizes
    0.07
     utilizing
    0.07
    _METADATA
    0.07
    _cut
    0.07
     laboratory
    0.07
    empresa
    0.07
    .AutoScale
    0.07
    Act Density 0.032%

    No Known Activations