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

    Neuronpedia

    INDEX
    Explanations

    numbers and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1
    0.60
    </th>
    0.56
    }",
    0.53
    }$,
    0.52
    ב
    0.49
    }>
    0.49
    0
    0.48
     Armee
    0.46
     M
    0.43
     H
    0.43
    POSITIVE LOGITS
    .
    0.68
     ذریع
    0.52
    ुरा
    0.51
    .³
    0.49
     demande
    0.47
     rappro
    0.46
    .​​
    0.46
    ٣
    0.46
     chaîne
    0.46
     forearm
    0.46
    Act Density 1.225%

    No Known Activations