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

    Neuronpedia

    INDEX
    Explanations

    specific word choice or phrasing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     posizione
    0.53
     maggiore
    0.52
     abortion
    0.51
    esimo
    0.50
     tradizione
    0.49
     sito
    0.48
     espécies
    0.48
     estructura
    0.47
     abort
    0.47
     độ
    0.47
    POSITIVE LOGITS
    Result
    0.54
    Nation
    0.51
    Simulation
    0.49
    Anthrop
    0.47
    Product
    0.46
    Refresh
    0.46
    Sampling
    0.46
    Middleware
    0.46
    Mel
    0.45
    Loved
    0.44
    Act Density 0.001%

    No Known Activations