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

    Neuronpedia

    INDEX
    Explanations

    rom

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     illusions
    -0.08
    檞
    -0.07
    -Origin
    -0.07
     toItem
    -0.07
    ",'
    -0.06
    odge
    -0.06
    фан
    -0.06
     أكبر
    -0.06
     Midnight
    -0.06
     asylum
    -0.06
    POSITIVE LOGITS
    .dtp
    0.08
    Pat
    0.07
    記
    0.07
    емых
    0.07
    昌
    0.07
    etails
    0.07
    :)])
    0.07
    晨
    0.06
    bite
    0.06
    _rel
    0.06
    Act Density 0.001%

    No Known Activations