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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /device
    -0.07
    司
    -0.06
    esign
    -0.06
     врач
    -0.06
    �
    -0.06
    ัฐบาล
    -0.06
     Desc
    -0.06
    -0.06
     zoals
    -0.06
    .visitInsn
    -0.06
    POSITIVE LOGITS
    rov
    0.07
    $body
    0.07
     spins
    0.07
     Wayne
    0.07
    ':
    0.06
    anonymous
    0.06
    osh
    0.06
    39
    0.06
    	fi
    0.06
    ATABASE
    0.06
    Act Density 0.009%

    No Known Activations