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

    Neuronpedia

    INDEX
    Explanations

    “

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Affairs
    -0.07
     Melee
    -0.06
    mares
    -0.06
    .Objects
    -0.06
    Unnamed
    -0.06
     McKay
    -0.06
    ?)↵
    -0.06
    esture
    -0.06
    Chooser
    -0.06
    ,',
    -0.06
    POSITIVE LOGITS
     производ
    0.07
    덕
    0.07
    	port
    0.07
     ظرف
    0.07
     improperly
    0.06
     ret
    0.06
    GBP
    0.06
     �
    0.06
    decay
    0.06
    .ob
    0.06
    Act Density 0.057%

    No Known Activations