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

    Neuronpedia

    INDEX
    Explanations

    Evaluation and comparison

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     없음
    -0.07
     pozor
    -0.07
    	user
    -0.07
     워
    -0.06
    	Me
    -0.06
     term
    -0.06
     نوش
    -0.06
    ерп
    -0.06
    シ
    -0.06
    (Property
    -0.06
    POSITIVE LOGITS
    \param
    0.07
    phins
    0.07
     gri
    0.07
    ellipse
    0.07
    'value
    0.07
    centre
    0.06
     woke
    0.06
     msgid
    0.06
     initialValues
    0.06
     stepper
    0.06
    Act Density 0.075%

    No Known Activations