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

    Neuronpedia

    INDEX
    Explanations

    stories characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    可能
    -0.07
    頭
    -0.06
     lose
    -0.06
    brick
    -0.06
     Frames
    -0.06
     righteousness
    -0.06
     snap
    -0.06
     Ramos
    -0.06
    คล
    -0.06
     kapsamında
    -0.06
    POSITIVE LOGITS
    .Positive
    0.07
    еса
    0.06
     emptied
    0.06
    cela
    0.06
    //--------------------------------
    0.06
    τον
    0.06
    (ne
    0.06
    ="../
    0.06
     atroc
    0.06
     TextArea
    0.06
    Act Density 0.171%

    No Known Activations