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

    Neuronpedia

    INDEX
    Explanations

    actions in lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     impartiality
    0.43
     morals
    0.42
     apostolic
    0.42
     opio
    0.39
     sanctity
    0.39
     Admit
    0.38
     disabilities
    0.38
    decimals
    0.38
     Reven
    0.37
     cleanliness
    0.37
    POSITIVE LOGITS
     regroup
    0.45
     analysed
    0.44
    㐬
    0.44
     رہنے
    0.42
     ગા
    0.41
    濆
    0.41
    管理的
    0.41
    转换
    0.40
    ëren
    0.40
    眅
    0.39
    Act Density 0.254%

    No Known Activations