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

    Neuronpedia

    INDEX
    Explanations

    ready

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ında
    -0.08
    .MONTH
    -0.06
    摆
    -0.06
    Regular
    -0.06
    Mountain
    -0.06
     które
    -0.06
    endid
    -0.06
    Persist
    -0.06
    fabric
    -0.06
    emmel
    -0.06
    POSITIVE LOGITS
     Duel
    0.07
    .Connect
    0.07
    .Obj
    0.06
    -workers
    0.06
     champ
    0.06
     recurring
    0.06
    .int
    0.06
     Decode
    0.06
    $key
    0.06
     conveying
    0.06
    Act Density 0.063%

    No Known Activations