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

    Neuronpedia

    INDEX
    Explanations

    Random text/sentences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     دي
    -0.08
    園
    -0.07
    卫
    -0.07
    hea
    -0.06
    Saudi
    -0.06
    ILITY
    -0.06
     buc
    -0.06
    }`
    -0.06
    meni
    -0.06
    мени
    -0.06
    POSITIVE LOGITS
    열
    0.07
     saison
    0.06
     vé
    0.06
     šest
    0.06
     Times
    0.06
     downturn
    0.06
    resolution
    0.06
     discharge
    0.06
    .mode
    0.06
    odě
    0.06
    Act Density 0.000%

    No Known Activations