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

    Neuronpedia

    INDEX
    Explanations

    definitions, hypotheses, or entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    reflection
    0.47
    faculty
    0.44
    addressed
    0.44
    run
    0.44
    address
    0.43
    interactive
    0.43
    issue
    0.42
    review
    0.42
    ز
    0.42
    serious
    0.42
    POSITIVE LOGITS
     prevision
    0.55
     WILLIAM
    0.48
     headroom
    0.47
    鋏
    0.46
    atoare
    0.44
     Barbosa
    0.44
     BEN
    0.44
    笽
    0.44
     airbags
    0.43
     EVER
    0.43
    Act Density 0.000%

    No Known Activations