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

    Neuronpedia

    INDEX
    Explanations

    Leaving

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Sele
    -0.08
     bene
    -0.07
     kone
    -0.07
    联通
    -0.07
    ன
    -0.07
    �
    -0.06
     Tài
    -0.06
    ambah
    -0.06
     tenure
    -0.06
    ソン
    -0.06
    POSITIVE LOGITS
    .clf
    0.07
     launcher
    0.07
     client
    0.07
    магаз
    0.07
    highest
    0.07
    هدف
    0.07
    startIndex
    0.07
    ốn
    0.07
     Classes
    0.07
    nement
    0.06
    Act Density 0.024%

    No Known Activations