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

    Neuronpedia

    INDEX
    Explanations

    list items start or end

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    衵
    0.39
    izontal
    0.38
     وهذا
    0.37
    ValueOf
    0.36
    جاه
    0.36
    Appending
    0.35
    Virtualized
    0.35
    akon
    0.35
    മാനം
    0.35
    apanicola
    0.34
    POSITIVE LOGITS
     pay
    0.43
     or
    0.39
     neuromuscular
    0.39
     importantes
    0.38
     tri
    0.37
     majors
    0.37
     principles
    0.37
     strollers
    0.36
     counterparts
    0.35
     ep
    0.35
    Act Density 0.087%

    No Known Activations