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

    Neuronpedia

    INDEX
    Explanations

    itation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     участ
    -0.07
    pic
    -0.07
    Arc
    -0.06
    航道
    -0.06
     bunny
    -0.06
     �
    -0.06
    PIC
    -0.06
    isson
    -0.06
     �
    -0.06
     работ
    -0.06
    POSITIVE LOGITS
     seasoning
    0.07
     weakening
    0.07
    옷
    0.07
    телем
    0.07
    modelName
    0.07
    reibung
    0.07
    [temp
    0.06
     Greeks
    0.06
    %p
    0.06
     prevention
    0.06
    Act Density 0.002%

    No Known Activations