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

    Neuronpedia

    INDEX
    Explanations

    assigning blame

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    爱好
    0.37
     কোম
    0.37
    牙
    0.37
    鏘
    0.37
    setDisplay
    0.37
    რივი
    0.36
     ergodic
    0.36
    ρον
    0.35
     Lub
    0.34
    PickerDialog
    0.34
    POSITIVE LOGITS
     blame
    3.13
     blaming
    2.91
     blames
    2.73
     blamed
    2.66
     culp
    1.69
     scape
    1.66
     attributing
    1.58
     culpa
    1.53
     attribution
    1.49
     fault
    1.43
    Act Density 0.052%

    No Known Activations