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

    Neuronpedia

    INDEX
    Explanations

    mathematical computations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    怎么办
    -0.08
     ?",
    -0.08
     nevertheless
    -0.08
     trotzdem
    -0.07
     Nevertheless
    -0.07
     CPR
    -0.07
    .um
    -0.07
    >",
    -0.07
    」「
    -0.07
    .ch
    -0.07
    POSITIVE LOGITS
     degelijk
    0.09
     यही
    0.08
     geg
    0.08
     hore
    0.08
    factor
    0.08
     :)
    0.08
    makes
    0.08
     inderdaad
    0.07
     blom
    0.07
     indeed
    0.07
    Act Density 0.087%

    No Known Activations