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

    Neuronpedia

    INDEX
    Explanations

    ob

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sluts
    -0.07
     hấp
    -0.07
    component
    -0.07
    -0.06
    Parcel
    -0.06
    一大堆
    -0.06
    뭐
    -0.06
     Stamina
    -0.06
    ⚪
    -0.06
     estilo
    -0.06
    POSITIVE LOGITS
     Sarah
    0.07
     Bailey
    0.07
    xea
    0.07
     conserv
    0.07
    alley
    0.06
    +c
    0.06
    Sean
    0.06
    )");↵
    0.06
     ben
    0.06
    OrCreate
    0.06
    Act Density 0.682%

    No Known Activations