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

    Neuronpedia

    INDEX
    Explanations

    hackers and likely outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     insecticide
    0.48
     Stap
    0.47
     prognosis
    0.47
     staple
    0.46
     Willie
    0.46
     항
    0.45
     Shark
    0.45
     range
    0.44
     hurdle
    0.44
     tuna
    0.44
    POSITIVE LOGITS
    ني
    0.62
    ر
    0.55
    omer
    0.51
     regretted
    0.50
     slecht
    0.50
    اين
    0.50
    atoren
    0.49
    erver
    0.49
     accuses
    0.49
    átiles
    0.49
    Act Density 0.000%

    No Known Activations