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

    Neuronpedia

    INDEX
    Explanations

    fill out form

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     space
    0.52
    espace
    0.49
     espaço
    0.49
     χώ
    0.49
     пространства
    0.48
     interview
    0.46
    收集
    0.46
    space
    0.45
     input
    0.44
     empty
    0.44
    POSITIVE LOGITS
     완
    0.55
     कंप्लीट
    0.47
     hoàn
    0.45
    完
    0.44
     informes
    0.43
    দেন
    0.42
     Complete
    0.41
     completos
    0.41
     Comple
    0.41
    COMPLETE
    0.40
    Act Density 0.005%

    No Known Activations