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

    Neuronpedia

    INDEX
    Explanations

    acknowledging ownership

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nonlinear
    0.42
    <unused98>
    0.42
     करणारे
    0.40
    顿
    0.40
    หมาย
    0.40
     ค
    0.39
     നേതൃ
    0.39
    orthogonal
    0.39
     тощо
    0.39
    0.39
    POSITIVE LOGITS
     annealed
    0.48
     fabrik
    0.46
     arrivée
    0.45
     piş
    0.45
    leş
    0.44
     puna
    0.44
     Miramar
    0.44
    вшись
    0.43
     SARS
    0.43
     ইচ্ছা
    0.42
    Act Density 0.002%

    No Known Activations