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

    Neuronpedia

    INDEX
    Explanations

    danger, death, killed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     exit
    0.53
     opacity
    0.52
     sprites
    0.50
     hygiene
    0.49
     autoclave
    0.49
     namespaces
    0.48
     appealing
    0.47
     missionaries
    0.47
     pren
    0.46
     guidance
    0.45
    POSITIVE LOGITS
    níci
    0.52
     Gradually
    0.51
     देता
    0.49
     同时
    0.48
     Meanwhile
    0.47
     ਕੋ
    0.46
     Bryson
    0.46
     Simultaneously
    0.45
     Polit
    0.45
    itl
    0.45
    Act Density 0.002%

    No Known Activations