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

    Neuronpedia

    INDEX
    Explanations

    Numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Animate
    -0.07
    あれ
    -0.07
    (cfg
    -0.07
     Mack
    -0.07
     //--
    -0.07
    潾
    -0.06
    (lp
    -0.06
     mentioning
    -0.06
     Verg
    -0.06
    פועל
    -0.06
    POSITIVE LOGITS
    Wel
    0.08
    kel
    0.08
     rolled
    0.07
    session
    0.07
    rocket
    0.07
    Et
    0.07
    prompt
    0.07
     Area
    0.07
     ent
    0.07
     Tablet
    0.07
    Act Density 0.008%

    No Known Activations