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

    Neuronpedia

    INDEX
    Explanations

    iterate, compare, specify

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Your
    0.94
     vostro
    0.90
    YOUR
    0.90
    Traditional
    0.88
    Typical
    0.86
    Votre
    0.85
     می‌توانید
    0.85
    を活用
    0.84
     vostra
    0.84
     Your
    0.82
    POSITIVE LOGITS
     `
    1.29
     (`
    1.16
     {@
    1.14
    遍历
    1.06
    (`
    1.05
     NaN
    0.99
     specified
    0.99
    `
    0.98
    ."""
    0.98
     指定
    0.97
    Act Density 1.897%

    No Known Activations