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

    Neuronpedia

    INDEX
    Explanations

    divided

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     NVIDIA
    -0.07
    -fr
    -0.06
    уск
    -0.06
    eries
    -0.06
    andom
    -0.06
    Science
    -0.06
    illaume
    -0.06
     Gor
    -0.06
    ولی
    -0.06
    ятий
    -0.06
    POSITIVE LOGITS
    SerializedName
    0.07
    	Intent
    0.07
    ]->
    0.06
    Cl
    0.06
    .getDeclared
    0.06
    	mp
    0.06
     suf
    0.06
     Clare
    0.06
     Leah
    0.06
     fostering
    0.06
    Act Density 0.016%

    No Known Activations