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

    Neuronpedia

    INDEX
    Explanations

    descriptive modifiers and specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lifts
    0.50
    sistema
    0.50
    in
    0.49
    hotels
    0.49
    questa
    0.49
    sure
    0.48
    system
    0.48
    orts
    0.47
    tug
    0.46
    н
    0.46
    POSITIVE LOGITS
     dinn
    0.55
    Durante
    0.51
     sampled
    0.49
     aead
    0.49
     liberated
    0.48
     splashed
    0.48
     represented
    0.47
    ირო
    0.47
     detained
    0.47
     neka
    0.46
    Act Density 0.000%

    No Known Activations