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

    Neuronpedia

    INDEX
    Explanations

    research replication

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     săn
    -0.08
    _remaining
    -0.08
    otherapy
    -0.07
    ACLE
    -0.07
    อยู่
    -0.07
     flattened
    -0.07
     leftover
    -0.07
    Anime
    -0.07
    Pocket
    -0.07
     pocket
    -0.07
    POSITIVE LOGITS
     reproduc
    0.16
     reproduction
    0.15
     reproduce
    0.15
     replication
    0.15
     replic
    0.14
     reprodu
    0.14
     replicate
    0.13
     reproduced
    0.12
     reprodução
    0.12
     восп
    0.12
    Act Density 0.011%

    No Known Activations