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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	Type
    -0.06
     zinc
    -0.06
    ัวร
    -0.06
    .external
    -0.06
     comun
    -0.06
     lỗi
    -0.06
     "-//
    -0.06
     late
    -0.06
    ory
    -0.06
     compound
    -0.06
    POSITIVE LOGITS
     Ви
    0.07
     Seg
    0.07
    ',{↵
    0.07
    'value
    0.07
     существует
    0.06
     Create
    0.06
     "}↵
    0.06
    _LARGE
    0.06
    wy
    0.06
    ители
    0.06
    Act Density 0.000%

    No Known Activations