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

    Neuronpedia

    INDEX
    Explanations

    Me can poet

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     are
    0.57
     gaskets
    0.53
     glands
    0.46
    0.46
    oves
    0.45
     miniatures
    0.45
     dungeons
    0.45
    规定
    0.44
     Studium
    0.44
    begin
    0.44
    POSITIVE LOGITS
     glavni
    0.63
     ellos
    0.55
     Меня
    0.55
     activar
    0.55
     Serviço
    0.54
     movimiento
    0.54
     দেশকে
    0.54
     nombre
    0.52
     serangan
    0.52
     bilgi
    0.51
    Act Density 0.000%

    No Known Activations