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

    Neuronpedia

    INDEX
    Explanations

    harm or negative consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     smothered
    0.50
    不
    0.48
    DefineConstants
    0.46
     millionaire
    0.46
    loud
    0.45
    omatic
    0.44
    ять
    0.44
    ப்பன்
    0.44
     deft
    0.43
    appan
    0.43
    POSITIVE LOGITS
     Lei
    0.47
     are
    0.46
     kø
    0.45
     ports
    0.45
    și
    0.45
     Rä
    0.44
     chi
    0.44
     গ
    0.43
     Ray
    0.43
     zichzelf
    0.43
    Act Density 0.002%

    No Known Activations