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

    Neuronpedia

    INDEX
    Explanations

    numbers and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    نامه
    0.37
    кій
    0.36
    ⥤
    0.35
     essentially
    0.35
    医院
    0.33
     básicamente
    0.32
    лені
    0.32
    щают
    0.32
     spectrom
    0.32
     permettent
    0.32
    POSITIVE LOGITS
    ele
    0.43
     )
    0.39
     .
    0.39
     ).
    0.39
     ",
    0.38
    ada
    0.37
    mn
    0.37
    iro
    0.37
     english
    0.37
    ez
    0.37
    Act Density 0.076%

    No Known Activations