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

    Neuronpedia

    INDEX
    Explanations

    threat protection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ძალი
    0.44
    ibir
    0.43
     proteção
    0.43
     biên
    0.42
    悅
    0.42
     proteger
    0.41
     보호
    0.41
     冖
    0.41
     ইতিহাসে
    0.41
     защиту
    0.41
    POSITIVE LOGITS
     ==
    0.43
     document
    0.41
     Pulitzer
    0.38
     Spal
    0.38
     Robert
    0.38
     IS
    0.37
     architecture
    0.37
     pum
    0.36
     arc
    0.35
    ↵
    0.35
    Act Density 0.000%

    No Known Activations