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

    Neuronpedia

    INDEX
    Explanations

    negative context and specific outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ArchiveAction
    0.51
    联动
    0.51
    offre
    0.48
    ądź
    0.48
    فانه
    0.47
    Transicao
    0.46
     capire
    0.46
    Citizen
    0.46
    zecz
    0.46
    Middle
    0.45
    POSITIVE LOGITS
     und
    0.44
     strontium
    0.42
     دی
    0.41
     missiles
    0.41
     ١
    0.41
     cesium
    0.40
     دیا۔
    0.40
    ¹.
    0.40
     missile
    0.40
     و
    0.40
    Act Density 0.002%

    No Known Activations