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

    Neuronpedia

    INDEX
    Explanations

    escalation or elaboration after initial action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    0.60
    ung
    0.49
    uv
    0.48
    ue
    0.46
    ortium
    0.46
    ir
    0.44
    ина
    0.44
    un
    0.44
    id
    0.43
    imod
    0.42
    POSITIVE LOGITS
    镞
    0.49
    ضافة
    0.46
     núi
    0.46
    ネジ
    0.45
    ະພັນ
    0.43
     wealthiest
    0.42
     filth
    0.42
     Đế
    0.42
     visione
    0.42
    饷
    0.42
    Act Density 0.008%

    No Known Activations