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

    Neuronpedia

    INDEX
    Explanations

    Academy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     )}↵↵
    -0.07
    /"↵↵
    -0.07
    wt
    -0.07
    MH
    -0.06
    /un
    -0.06
     stagnant
    -0.06
    ------↵↵
    -0.06
    fect
    -0.06
     *)↵↵
    -0.06
    建设
    -0.06
    POSITIVE LOGITS
     casinos
    0.07
     &#
    0.06
    ]).
    0.06
    ISTICS
    0.06
     LETTER
    0.06
    enment
    0.06
    veriş
    0.06
     FOUR
    0.06
    supported
    0.06
     TEN
    0.06
    Act Density 0.017%

    No Known Activations