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

    Neuronpedia

    INDEX
    Explanations

    minimize risk or harm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     طریق
    0.38
     આગળ
    0.38
    ewną
    0.38
     Salts
    0.37
     शीर्ष
    0.37
     salts
    0.37
    Chess
    0.37
    ஸல்
    0.37
    谢
    0.36
    ając
    0.36
    POSITIVE LOGITS
     totalling
    0.41
     lagoon
    0.39
     nta
    0.38
     [['
    0.38
     మొత్త
    0.38
     [%
    0.38
    ɺ
    0.37
     pervasive
    0.36
    seab
    0.36
     downgraded
    0.36
    Act Density 0.000%

    No Known Activations