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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    riting
    -0.08
    pired
    -0.07
    how
    -0.07
    >e
    -0.07
     alguien
    -0.07
     Ana
    -0.07
    ène
    -0.07
     allergic
    -0.07
    未來
    -0.07
    �
    -0.07
    POSITIVE LOGITS
    踌
    0.07
     exhibitions
    0.07
     Regions
    0.07
    进驻
    0.07
    ﮯ
    0.07
    狳
    0.07
     interv
    0.06
     gradu
    0.06
    溶
    0.06
    LLU
    0.06
    Act Density 0.002%

    No Known Activations