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

    Neuronpedia

    INDEX
    Explanations

    company names or organizations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    技術
    0.36
     Sval
    0.35
    poles
    0.34
     BBC
    0.34
     MBE
    0.33
    gram
    0.33
     ober
    0.32
    महारा
    0.32
     Tiv
    0.32
    no
    0.32
    POSITIVE LOGITS
     प्रमो
    0.39
     предлагают
    0.37
     đề
    0.36
    蹺
    0.36
    ąż
    0.35
    ασίας
    0.33
     विष
    0.33
    °)
    0.33
    zię
    0.33
     invitación
    0.32
    Act Density 0.001%

    No Known Activations