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

    Neuronpedia

    INDEX
    Explanations

    "Guide to" phrase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cauza
    0.43
     motto
    0.42
     sadde
    0.40
    automat
    0.40
     goble
    0.40
    ferencia
    0.39
     biais
    0.39
     poema
    0.38
     hormati
    0.38
     bailar
    0.38
    POSITIVE LOGITS
     Understanding
    0.73
     surviving
    0.72
    Understanding
    0.72
     understanding
    0.71
     Mastering
    0.67
     navigating
    0.63
     Designing
    0.63
     Surv
    0.60
    understanding
    0.60
     Successful
    0.59
    Act Density 0.002%

    No Known Activations