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

    Neuronpedia

    INDEX
    Explanations

    inflict harm, suffering, death

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     令
    0.39
    IER
    0.38
    edited
    0.37
    様
    0.37
     ویر
    0.37
    പ്പറ
    0.36
    memberNameLink
    0.36
    situation
    0.36
    CreateWall
    0.36
    interior
    0.36
    POSITIVE LOGITS
     argentinos
    0.47
     Africans
    0.44
     Armour
    0.43
    XS
    0.42
     Achilles
    0.41
     Koreans
    0.40
    oterapia
    0.40
     reminded
    0.39
    чками
    0.39
     repet
    0.38
    Act Density 0.000%

    No Known Activations