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

    Neuronpedia

    INDEX
    Explanations

    thus

    np_acts-logits-general · gemini-2.5-flash-lite

    Roleplay instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    this
    0.61
    that
    0.55
    ６
    0.50
    六
    0.50
    n
    0.49
    6
    0.49
    on
    0.48
     फंडा
    0.48
    न
    0.48
    p
    0.48
    POSITIVE LOGITS
     in
    0.65
    льных
    0.58
     giardino
    0.54
     في
    0.52
    льной
    0.52
     д
    0.51
     feeding
    0.51
     במ
    0.51
     hiszen
    0.50
    ской
    0.49
    Act Density 0.000%

    No Known Activations