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

    Neuronpedia

    INDEX
    Explanations

    passwords

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ाइव
    -0.06
     Acrobat
    -0.06
    /ng
    -0.06
     ph
    -0.06
    Diagram
    -0.06
    sel
    -0.06
     Loch
    -0.05
     =>$
    -0.05
     conducive
    -0.05
     الو
    -0.05
    POSITIVE LOGITS
     owned
    0.08
     hỏi
    0.07
     Володими
    0.07
    ＼
    0.06
    RIX
    0.06
    concept
    0.06
    average
    0.06
    ======↵
    0.06
    ession
    0.06
     execut
    0.06
    Act Density 0.026%

    No Known Activations