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

    Neuronpedia

    INDEX
    Explanations

    SQL injection attempt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⴱ
    0.53
     встречи
    0.52
    ूल
    0.52
    テナンス
    0.50
    ография
    0.49
     رہنما
    0.49
     този
    0.49
    ュ
    0.47
    ሼ
    0.47
    का
    0.46
    POSITIVE LOGITS
     protrusion
    0.52
     se
    0.44
    }{
    0.44
     in
    0.43
     byte
    0.43
     envi
    0.43
    `:
    0.43
    ;
    0.43
    _{-
    0.42
     profitability
    0.41
    Act Density 0.000%

    No Known Activations