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

    Neuronpedia

    INDEX
    Explanations

    providing descriptions and details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🏽
    0.41
    Ex
    0.40
    regs
    0.40
     جم
    0.38
    сиз
    0.38
    세요
    0.37
    elements
    0.37
    магази
    0.37
    IDGE
    0.36
    Foe
    0.36
    POSITIVE LOGITS
     medias
    0.42
     timescales
    0.41
     조직
    0.40
     reflexión
    0.40
    മ്പോ
    0.40
     terres
    0.39
    प्ल
    0.39
     anarch
    0.38
     Su
    0.38
     tasas
    0.38
    Act Density 0.059%

    No Known Activations