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

    Neuronpedia

    INDEX
    Explanations

    cultural innovation and less strictness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Break
    0.40
     Successfully
    0.40
    Break
    0.39
     bazaar
    0.39
     μετα
    0.39
     перехода
    0.39
     Caesar
    0.38
     Burgers
    0.38
     Commander
    0.38
    BuildAction
    0.38
    POSITIVE LOGITS
    ങ്ങള
    0.44
    OGO
    0.41
    endorong
    0.39
    ว้าง
    0.39
    দানি
    0.38
    kových
    0.38
     mendorong
    0.37
    writerow
    0.37
    khov
    0.37
     debate
    0.37
    Act Density 0.001%

    No Known Activations