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

    Neuronpedia

    INDEX
    Explanations

    Ari, tri, Bri, cri, Sri beginnings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     marcador
    0.39
     signalled
    0.37
     stron
    0.37
     bleak
    0.37
     thơ
    0.36
     busses
    0.36
     INV
    0.36
     poč
    0.35
     signaled
    0.35
     promen
    0.35
    POSITIVE LOGITS
     भरी
    0.44
    ޯ
    0.42
    another
    0.41
    ega
    0.41
    ks
    0.40
    Fri
    0.40
    奥
    0.40
    answ
    0.40
    evolution
    0.40
    anna
    0.39
    Act Density 0.030%

    No Known Activations