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

    Neuronpedia

    INDEX
    Explanations

    correlated

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Freedom
    -0.07
     astore
    -0.06
    استان
    -0.06
     반환
    -0.06
     remaining
    -0.06
     Hip
    -0.06
     mote
    -0.06
     �
    -0.06
    ids
    -0.06
    +w
    -0.05
    POSITIVE LOGITS
    ISING
    0.07
     misdemean
    0.07
     Mỹ
    0.07
     /^
    0.07
    Really
    0.07
     Aqu
    0.06
    (number
    0.06
    [:-
    0.06
    ș
    0.06
    ctic
    0.06
    Act Density 0.000%

    No Known Activations