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

    Neuronpedia

    INDEX
    Explanations

    containment, inner

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    信誉
    -0.07
    partial
    -0.07
    aisie
    -0.07
    (Convert
    -0.07
    adda
    -0.07
    esser
    -0.07
     Entonces
    -0.07
     reliable
    -0.07
     partial
    -0.07
     korzyst
    -0.07
    POSITIVE LOGITS
     الداخلي
    0.11
     compartments
    0.10
    нут
    0.10
     глуб
    0.10
    ใจ
    0.09
     खोल
    0.09
     داخ
    0.09
     internos
    0.09
     gudaha
    0.09
     भीतर
    0.09
    Act Density 0.032%

    No Known Activations