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

    Neuronpedia

    INDEX
    Explanations

    abstract concepts and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -
    0.38
    0
    0.37
     its
    0.36
     the
    0.35
    0.35
     soccer
    0.32
    beat
    0.32
    2
    0.32
    /
    0.31
    3
    0.31
    POSITIVE LOGITS
     uiteindelijk
    0.41
     ankaŭ
    0.41
     często
    0.39
    လည်း
    0.38
     enables
    0.38
     також
    0.37
     также
    0.37
    သာ
    0.37
     često
    0.37
     వివిధ
    0.36
    Act Density 0.003%

    No Known Activations