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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     цель
    -0.06
     pillow
    -0.06
     [@
    -0.06
     України
    -0.06
     adversary
    -0.06
    ович
    -0.06
     通
    -0.06
     intensely
    -0.06
    ног
    -0.06
    仓
    -0.06
    POSITIVE LOGITS
    IR
    0.08
    GetString
    0.07
     Check
    0.07
    HasForeignKey
    0.07
     nationally
    0.07
     serving
    0.07
     Lux
    0.06
     */↵↵
    0.06
    tur
    0.06
    itar
    0.06
    Act Density 0.000%

    No Known Activations