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

    Neuronpedia

    INDEX
    Explanations

    fats

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ACCESS
    -0.07
     enrollment
    -0.07
    "H
    -0.06
     воно
    -0.06
    苦
    -0.06
    'I
    -0.06
     зараз
    -0.06
     curing
    -0.06
    ”
    -0.06
     wander
    -0.06
    POSITIVE LOGITS
    нен
    0.07
     fats
    0.07
    니다
    0.06
     Fat
    0.06
    jišť
    0.06
    ام
    0.06
    Someone
    0.06
     gi�
    0.06
     FH
    0.06
    ją
    0.06
    Act Density 0.002%

    No Known Activations