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

    Neuronpedia

    INDEX
    Explanations

    in public spaces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hini
    0.38
     bearish
    0.38
     sukham
    0.37
     deut
    0.37
     Philosoph
    0.36
     ነ
    0.36
     Pati
    0.36
     dụng
    0.36
     pessim
    0.36
     kesulitan
    0.36
    POSITIVE LOGITS
     أمام
    1.39
     delante
    1.34
     devant
    1.29
     davanti
    1.29
    面前
    1.26
     앞에서
    1.23
     publicly
    1.20
     frente
    1.20
     سامنے
    1.09
     সামনে
    1.05
    Act Density 0.015%

    No Known Activations