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

    Neuronpedia

    INDEX
    Explanations

    lists, programmatic, metrics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Hen
    0.37
    Added
    0.35
    )].
    0.35
     المز
    0.34
    accessdate
    0.33
     vorhand
    0.33
    Iz
    0.33
    esz
    0.32
    Signed
    0.32
    urized
    0.32
    POSITIVE LOGITS
     compound
    0.49
     COMPO
    0.48
     page
    0.47
    ページ
    0.47
     explore
    0.46
    compound
    0.46
     Compound
    0.44
     webpage
    0.42
    Compound
    0.42
     exploración
    0.41
    Act Density 0.000%

    No Known Activations