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

    Neuronpedia

    INDEX
    Explanations

    fined-tuned technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ika
    0.50
    δει
    0.48
    gar
    0.47
    цыя
    0.47
    epoch
    0.47
    archive
    0.46
    intuitive
    0.46
     آئینہ
    0.45
    appy
    0.44
    ged
    0.44
    POSITIVE LOGITS
     genotypes
    0.57
     protrusions
    0.55
     elytris
    0.53
     markup
    0.51
     bilirubin
    0.49
     carbohydrates
    0.48
     homomorphisms
    0.48
     shaders
    0.48
     mannitol
    0.48
     metabolism
    0.47
    Act Density 0.001%

    No Known Activations