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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hindered
    -0.07
     Undert
    -0.07
     Blind
    -0.07
     Coca
    -0.07
     nale
    -0.07
    /link
    -0.07
     verg
    -0.06
    ération
    -0.06
     đến
    -0.06
    ologické
    -0.06
    POSITIVE LOGITS
     Monster
    0.06
     tying
    0.06
    -st
    0.06
     relationship
    0.06
    ource
    0.05
    GO
    0.05
     بن
    0.05
     ft
    0.05
    forcing
    0.05
    TRACT
    0.05
    Act Density 0.025%

    No Known Activations