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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    แล้ว
    0.47
    尚未
    0.40
     déploy
    0.39
    नंतर
    0.38
     తీ
    0.36
     THEN
    0.36
     already
    0.35
    ាំង
    0.35
     уже
    0.35
    Then
    0.33
    POSITIVE LOGITS
    iy
    0.42
    bit
    0.40
    jed
    0.39
    bin
    0.38
    huana
    0.38
     सिप
    0.36
    ppen
    0.36
    iz
    0.36
    ています
    0.35
    گ
    0.35
    Act Density 0.000%

    No Known Activations