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

    Neuronpedia

    INDEX
    Explanations

    earth, mitochondria, watching

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    et
    0.64
    ul
    0.64
     for
    0.64
     Nu
    0.63
    ter
    0.60
     Bar
    0.58
    nu
    0.57
     Lock
    0.57
    au
    0.55
    em
    0.55
    POSITIVE LOGITS
    ли
    0.62
    га
    0.55
     миру
    0.54
    рд
    0.52
    rdoba
    0.50
     späteren
    0.50
     температура
    0.49
     пон
    0.48
    κης
    0.48
    мет
    0.48
    Act Density 0.000%

    No Known Activations