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

    Neuronpedia

    INDEX
    Explanations

    ulation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	cf
    -0.07
     rapidly
    -0.06
     gods
    -0.06
     eds
    -0.06
    ி
    -0.06
     existing
    -0.06
     satellite
    -0.06
     IX
    -0.06
    Sci
    -0.06
     dt
    -0.06
    POSITIVE LOGITS
    $item
    0.07
     견
    0.07
     ['-
    0.07
    rame
    0.07
    wie
    0.07
     Cover
    0.06
     Invitation
    0.06
    ountains
    0.06
     Пот
    0.06
    aryl
    0.06
    Act Density 0.179%

    No Known Activations