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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     labs
    -0.07
     through
    -0.07
     Checkbox
    -0.06
    ITES
    -0.06
     translator
    -0.06
    UD
    -0.06
    disconnect
    -0.06
     bills
    -0.06
    .sharedInstance
    -0.06
    -source
    -0.06
    POSITIVE LOGITS
    '])
    0.06
     Fortnite
    0.06
     конкрет
    0.06
    �
    0.06
    (-
    0.06
     requ
    0.06
    .Character
    0.06
     concentrates
    0.06
     isAdmin
    0.06
    ?,
    0.06
    Act Density 0.108%

    No Known Activations