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

    Neuronpedia

    INDEX
    Explanations

    favorite

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ibling
    -0.07
    “All
    -0.07
     Zimbabwe
    -0.07
    .problem
    -0.07
    .Sound
    -0.07
    쳬
    -0.07
     tiền
    -0.06
    .ci
    -0.06
    릴
    -0.06
    来找
    -0.06
    POSITIVE LOGITS
     AR
    0.07
    GORITHM
    0.07
    茯
    0.07
    awai
    0.07
    Newton
    0.06
     assert
    0.06
    Hotéis
    0.06
    .MODEL
    0.06
    偉
    0.06
    ULONG
    0.06
    Act Density 0.020%

    No Known Activations