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

    Neuronpedia

    INDEX
    Explanations

    Operation mission

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    㖦
    0.76
     feedbacks
    0.73
     checksum
    0.72
     साल
    0.72
     scratching
    0.70
    计算机
    0.70
    Bitcoin
    0.67
     Mlad
    0.67
     namespaces
    0.65
    ⑰
    0.65
    POSITIVE LOGITS
     traitor
    1.15
     Operation
    1.11
     valiant
    1.07
     torture
    1.07
     glorious
    1.04
     mission
    1.01
     missione
    0.98
     bribery
    0.97
     OPERATION
    0.97
     Mission
    0.96
    Act Density 0.134%

    No Known Activations