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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    瓀
    -0.07
    .th
    -0.07
    anne
    -0.07
    unter
    -0.07
    胴
    -0.07
     Convers
    -0.07
    UDIO
    -0.07
    猎
    -0.07
    熟
    -0.07
    STATIC
    -0.06
    POSITIVE LOGITS
    水量
    0.07
     hazard
    0.07
     turb
    0.06
    拧
    0.06
    .Column
    0.06
     Packages
    0.06
    .parameter
    0.06
     Reservation
    0.06
    (bs
    0.06
    监理
    0.06
    Act Density 0.011%

    No Known Activations