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

    Neuronpedia

    INDEX
    Explanations

    Software versioning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    اها
    -0.06
     rgba
    -0.06
    orch
    -0.06
     dés
    -0.06
    lore
    -0.06
    çuk
    -0.06
     arr
    -0.06
    	attr
    -0.06
    ustr
    -0.06
    loud
    -0.06
    POSITIVE LOGITS
    :YES
    0.07
     Voyage
    0.06
     runner
    0.06
     quadrant
    0.06
    .INSTANCE
    0.06
     screwed
    0.06
     bounty
    0.06
    -existing
    0.06
     кіль
    0.06
     Seamless
    0.06
    Act Density 0.004%

    No Known Activations