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

    Neuronpedia

    INDEX
    Explanations

    Create Repl

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aturally
    0.42
    thom
    0.40
    ธิ
    0.40
    rif
    0.39
    riters
    0.39
     คลิก
    0.38
    idem
    0.38
    akse
    0.38
     otak
    0.38
    ertura
    0.37
    POSITIVE LOGITS
     Lynne
    0.38
    数
    0.38
     수
    0.38
     ру
    0.38
     ون
    0.38
     significance
    0.37
     Wound
    0.37
    പേ
    0.36
     Millie
    0.36
     signific
    0.36
    Act Density 0.000%

    No Known Activations