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

    Neuronpedia

    INDEX
    Explanations

    property

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ANC
    -0.06
     बच
    -0.06
    жди
    -0.06
    وية
    -0.06
     ket
    -0.06
     действ
    -0.06
     abolished
    -0.06
     segregation
    -0.06
    不同
    -0.05
     volunt
    -0.05
    POSITIVE LOGITS
    mal
    0.07
    -util
    0.07
    IFIER
    0.07
    े।↵
    0.07
    Sharper
    0.07
     özellikleri
    0.07
    ELL
    0.07
     �
    0.07
     delighted
    0.06
    ằ
    0.06
    Act Density 0.017%

    No Known Activations