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
    -pack
    -0.06
     터
    -0.06
     bam
    -0.06
     estamos
    -0.06
    bast
    -0.06
    ),$
    -0.06
     gü
    -0.06
    RAR
    -0.06
    Graph
    -0.06
     spectator
    -0.06
    POSITIVE LOGITS
    lef
    0.07
    (attributes
    0.07
     Emb
    0.07
    thing
    0.07
    决定
    0.06
     Damian
    0.06
     što
    0.06
     przed
    0.06
     jen
    0.06
    意义
    0.06
    Act Density 0.005%

    No Known Activations