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

    Neuronpedia

    INDEX
    Explanations

    tensorflow

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ค
    -0.07
     beer
    -0.06
    对
    -0.06
     Financial
    -0.06
    という
    -0.06
    Pointer
    -0.06
     converter
    -0.06
     PACKAGE
    -0.06
     rider
    -0.06
     POINTER
    -0.06
    POSITIVE LOGITS
     Moist
    0.07
     classmates
    0.07
     exhausted
    0.07
     исч
    0.06
    ,tp
    0.06
     Моск
    0.06
    -redux
    0.06
    ροφορ
    0.06
     Interviews
    0.06
    .Focus
    0.06
    Act Density 0.005%

    No Known Activations