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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    onde
    -0.06
    月
    -0.06
    東
    -0.06
    _city
    -0.06
    maximum
    -0.06
    ・
    -0.06
    .gms
    -0.06
    东
    -0.06
     xem
    -0.06
    -Type
    -0.06
    POSITIVE LOGITS
    ctxt
    0.07
    FX
    0.06
     elev
    0.06
    ีโ
    0.06
     paginate
    0.06
     Coordinator
    0.06
     ↵		↵
    0.06
    ~-
    0.06
    DET
    0.06
     [.
    0.06
    Act Density 0.322%

    No Known Activations