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

    Neuronpedia

    INDEX
    Explanations

    parameter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _COUNTER
    -0.07
     nighttime
    -0.07
    toDate
    -0.07
     DataGridView
    -0.06
     freezes
    -0.06
     explosions
    -0.06
     libero
    -0.06
    actory
    -0.06
    .Lock
    -0.06
     örgüt
    -0.06
    POSITIVE LOGITS
     겁
    0.07
    -user
    0.06
     Cunningham
    0.06
    god
    0.06
    )?↵
    0.06
    ुट
    0.06
     Produkte
    0.06
    	email
    0.06
    amy
    0.06
    .Sys
    0.06
    Act Density 0.020%

    No Known Activations