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

    Neuronpedia

    INDEX
    Explanations

    xml encoding=

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     enroll
    0.34
     celebrate
    0.34
    лан
    0.34
    cpf
    0.34
    zäh
    0.34
    вый
    0.33
     وان
    0.32
     Enrollment
    0.32
    )/
    0.32
     Yuan
    0.32
    POSITIVE LOGITS
    rophages
    0.40
    suitable
    0.38
     thải
    0.38
    phthal
    0.38
    πων
    0.38
    ของคุณ
    0.37
     നമ്മുടെ
    0.36
     unserer
    0.35
    Bradley
    0.35
     unseres
    0.35
    Act Density 0.000%

    No Known Activations