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

    Neuronpedia

    INDEX
    Explanations

    create

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     waiter
    -0.06
    ρίας
    -0.06
     disclose
    -0.06
     facade
    -0.06
     bouquet
    -0.06
    .low
    -0.06
     Incorrect
    -0.06
    SEG
    -0.06
    �
    -0.06
    linkedin
    -0.06
    POSITIVE LOGITS
    heure
    0.07
     cultivated
    0.07
     angle
    0.06
    λικά
    0.06
    募
    0.06
    Rights
    0.06
    раб
    0.06
     rk
    0.06
     amazingly
    0.06
    Created
    0.06
    Act Density 0.028%

    No Known Activations