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

    Neuronpedia

    INDEX
    Explanations

    related to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pós
    0.54
    țional
    0.54
     فول
    0.53
     in
    0.52
    ätzen
    0.52
     हवे
    0.52
     လက်
    0.52
     في
    0.52
     மாண
    0.52
    5
    0.52
    POSITIVE LOGITS
     terkait
    0.88
     relacionados
    0.79
     relacionado
    0.75
    Related
    0.73
     envolvendo
    0.69
    に関連
    0.68
    t
    0.68
     melibatkan
    0.66
     related
    0.66
     relacionada
    0.66
    Act Density 0.138%

    No Known Activations