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

    Neuronpedia

    INDEX
    Explanations

    testimonials and recommendations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     core
    -0.07
    ему
    -0.06
    .Maximum
    -0.06
     exempt
    -0.06
     halls
    -0.06
    ому
    -0.06
     parece
    -0.06
    ervation
    -0.06
    ��
    -0.06
    _FR
    -0.06
    POSITIVE LOGITS
     yielding
    0.07
    د
    0.06
    Clinical
    0.06
    -w
    0.06
     것이다
    0.06
     switching
    0.06
    خص
    0.06
    /start
    0.06
    /Card
    0.05
     가까
    0.05
    Act Density 0.032%

    No Known Activations