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

    Neuronpedia

    INDEX
    Explanations

    future orientation, goal-oriented, print orientation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    د
    1.21
     or
    1.07
     is
    1.06
     in
    1.01
    s
    1.01
    ation
    1.00
     on
    1.00
    д
    0.98
     حد
    0.98
    ים
    0.93
    POSITIVE LOGITS
    ರ
    1.27
     powied
    1.19
     yoki
    0.99
    프트
    0.96
    ?
    0.96
    이니까
    0.92
    سی
    0.90
    つの
    0.90
    ジ
    0.90
     comenc
    0.89
    Act Density 0.096%

    No Known Activations