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

    Neuronpedia

    INDEX
    Explanations

    scientific method, risk appetite, panel discussions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    HeaderText
    0.44
     Interpre
    0.44
     tarses
    0.44
    قم
    0.42
     Turbulent
    0.41
    ໋
    0.40
     linéaires
    0.40
     حركة
    0.40
     emble
    0.39
     transitory
    0.39
    POSITIVE LOGITS
     другой
    0.51
     otro
    0.41
     другая
    0.40
     otra
    0.39
     говорил
    0.39
     másik
    0.39
     vreau
    0.38
     تومان
    0.38
    媜
    0.38
    在
    0.38
    Act Density 0.000%

    No Known Activations