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

    Neuronpedia

    INDEX
    Explanations

    want or need

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    walla
    0.46
     Climate
    0.43
     governments
    0.43
     Government
    0.41
    ipelago
    0.41
    inders
    0.40
    orm
    0.40
    Climate
    0.40
     Governments
    0.39
     syllables
    0.39
    POSITIVE LOGITS
    필
    0.47
     필
    0.45
     요소
    0.40
    旮
    0.40
     критери
    0.39
    응
    0.39
    변
    0.38
     Krit
    0.38
     moody
    0.37
    李
    0.37
    Act Density 0.000%

    No Known Activations