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

    Neuronpedia

    INDEX
    Explanations

    enough

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     repeating
    -0.07
     Sets
    -0.07
     (-
    -0.07
     Bern
    -0.07
    第二
    -0.07
     designated
    -0.07
    right
    -0.06
    不确定性
    -0.06
     indicates
    -0.06
     Odds
    -0.06
    POSITIVE LOGITS
     strm
    0.08
    managedType
    0.07
    SSF
    0.07
    安抚
    0.07
    ⏌
    0.07
    ,['
    0.07
     ole
    0.07
     trg
    0.07
    MSG
    0.07
     Spa
    0.06
    Act Density 0.015%

    No Known Activations