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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     techno
    -0.07
     metrics
    -0.06
    snapshot
    -0.06
    ]").
    -0.06
    cribes
    -0.06
    ]').
    -0.06
     highly
    -0.06
    政
    -0.06
     ern
    -0.06
    ]');↵
    -0.06
    POSITIVE LOGITS
    athering
    0.06
     Dolphin
    0.06
     Rever
    0.06
    ève
    0.06
    ビー
    0.06
     каж
    0.06
     Folk
    0.06
    .="<
    0.06
     Haiti
    0.06
     obtener
    0.06
    Act Density 0.015%

    No Known Activations