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

    Neuronpedia

    INDEX
    Explanations

    security technologies and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    agona
    0.44
    })
    0.41
    ible
    0.39
    atural
    0.39
    told
    0.39
    lus
    0.38
    });
    0.38
    GQ
    0.37
    ida
    0.37
     sasan
    0.37
    POSITIVE LOGITS
     Fairness
    0.43
     вперед
    0.36
     Loose
    0.36
    +](=
    0.36
     subcommand
    0.36
     ආරක්ෂ
    0.36
     পাথ
    0.35
     мире
    0.35
    一声
    0.35
    转发
    0.35
    Act Density 0.000%

    No Known Activations