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

    Neuronpedia

    INDEX
    Explanations

    concepts and entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    豢
    0.52
     szüks
    0.47
    헛
    0.47
    captivity
    0.46
     ಅಗತ್ಯ
    0.46
     वास्तविकता
    0.45
     효과
    0.45
    راتيج
    0.44
    切实
    0.44
     അയാള
    0.43
    POSITIVE LOGITS
     myself
    0.58
     comparing
    0.54
     minhas
    0.54
     during
    0.53
     we
    0.51
     my
    0.51
     ourselves
    0.50
     I
    0.49
     x
    0.49
     We
    0.49
    Act Density 0.000%

    No Known Activations