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

    Neuronpedia

    INDEX
    Explanations

    future possibility or outcome

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    或
    0.39
    または
    0.37
    ৰ
    0.36
    หรือ
    0.35
     বা
    0.35
    或者
    0.33
     или
    0.33
     utilisons
    0.33
    ຫຼື
    0.32
    により
    0.32
    POSITIVE LOGITS
     lose
    0.35
     become
    0.33
     encouraged
    0.32
     inevitably
    0.31
     본격
    0.31
     begin
    0.31
     invite
    0.31
     empezar
    0.29
     reminiscent
    0.29
     begun
    0.29
    Act Density 0.130%

    No Known Activations