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

    Neuronpedia

    INDEX
    Explanations

    Researcher affiliations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     WebSocket
    -0.07
     Qualified
    -0.07
    _card
    -0.07
     Liberty
    -0.07
    _account
    -0.07
    Writer
    -0.07
     Medicare
    -0.07
     qualified
    -0.07
     write
    -0.06
     squadron
    -0.06
    POSITIVE LOGITS
     bursting
    0.07
     赤
    0.06
    ,proto
    0.06
     kteří
    0.06
     Smooth
    0.06
    #c
    0.06
     dragging
    0.06
     jug
    0.06
     alph
    0.06
     піш
    0.05
    Act Density 0.011%

    No Known Activations