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

    Neuronpedia

    INDEX
    Explanations

    questions starting with what

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     extruder
    0.43
     brisket
    0.42
     aard
    0.40
     adjustable
    0.40
     wrest
    0.40
     concedes
    0.39
     coyote
    0.39
     movable
    0.39
     progreso
    0.39
     conceding
    0.39
    POSITIVE LOGITS
     Characteristic
    0.42
     ลักษณะ
    0.41
    ising
    0.40
     ή
    0.40
     Characteristics
    0.40
     पहले
    0.40
     หรือ
    0.40
     Psychology
    0.40
    (),
    0.39
    叫做
    0.39
    Act Density 0.001%

    No Known Activations