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

    Neuronpedia

    INDEX
    Explanations

    virtual addresses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bowl
    -0.10
     Bowl
    -0.10
     bowls
    -0.09
     Bow
    -0.08
     إعلان
    -0.08
     tion
    -0.08
     vid
    -0.08
    টির
    -0.07
     بور
    -0.07
     frais
    -0.07
    POSITIVE LOGITS
     regulate
    0.07
    169
    0.07
    233
    0.07
     cori
    0.07
     எண்ண
    0.07
     regulated
    0.07
    space
    0.07
     parted
    0.07
     chiefs
    0.07
    ishni
    0.07
    Act Density 0.001%

    No Known Activations