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

    Neuronpedia

    INDEX
    Explanations

    part or highlight

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dziewcz
    -0.08
     setContentView
    -0.07
     זקוק
    -0.07
    VG
    -0.07
     홈페이지
    -0.07
     excited
    -0.07
    Built
    -0.07
     manpower
    -0.07
    Soap
    -0.06
     visa
    -0.06
    POSITIVE LOGITS
    **/↵↵
    0.07
    olle
    0.07
    ‐
    0.06
    ool
    0.06
    -↵↵
    0.06
     рублей
    0.06
    ustral
    0.06
    ałem
    0.06
     الثلاث
    0.06
    endi
    0.06
    Act Density 0.052%

    No Known Activations