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

    Neuronpedia

    INDEX
    Explanations

    humanitarian aid and crises

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ophytic
    0.52
    selecting
    0.49
    idos
    0.48
     viviendas
    0.48
    otoxic
    0.47
    ceived
    0.47
    igning
    0.46
    靭
    0.46
    sellers
    0.46
    がなく
    0.46
    POSITIVE LOGITS
     Humanitarian
    0.70
    outes
    0.68
     humanitarian
    0.64
     famine
    0.58
     Envoy
    0.58
     wardrobe
    0.56
     is
    0.55
     vanuit
    0.55
     from
    0.54
     depuis
    0.54
    Act Density 0.007%

    No Known Activations