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

    Neuronpedia

    INDEX
    Explanations

    finding a solution or way

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     বরাবর
    0.42
    ற்ப
    0.41
    бая
    0.39
    ptăm
    0.39
     సార
    0.39
    缃
    0.37
     perteneciente
    0.37
    ਐ
    0.37
     മഹാ
    0.37
     gehad
    0.37
    POSITIVE LOGITS
    نما
    0.61
    نم
    0.61
     آسان
    0.55
     easy
    0.52
     حل
    0.49
    ง่าย
    0.49
    escape
    0.47
    正确
    0.47
     escape
    0.47
    حل
    0.47
    Act Density 0.003%

    No Known Activations