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

    Neuronpedia

    INDEX
    Explanations

    matter type, operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ne
    0.33
     गुण
    0.33
    📨
    0.33
    ㄗ
    0.33
    Carlo
    0.32
    Daten
    0.32
    န်း
    0.31
     povinn
    0.31
    Nickel
    0.31
    Fac
    0.31
    POSITIVE LOGITS
     такого
    0.36
     അവരുടെ
    0.36
     குடும்ப
    0.32
     Remix
    0.31
     family
    0.31
     Sommer
    0.30
     ;$
    0.30
    iswa
    0.30
     seasoning
    0.29
     IS
    0.29
    Act Density 0.107%

    No Known Activations