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
     drifting
    -0.07
     protective
    -0.07
    erm
    -0.06
     navig
    -0.06
     Fly
    -0.06
    zier
    -0.06
     pharmacist
    -0.06
    Emily
    -0.06
    .energy
    -0.06
     모
    -0.06
    POSITIVE LOGITS
    —
    0.08
    重大
    0.07
    人民
    0.06
    τέρα
    0.06
    0.06
    FW
    0.06
    届
    0.06
    vements
    0.06
    _SER
    0.06
    |/
    0.06
    Act Density 0.003%

    No Known Activations