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

    Neuronpedia

    INDEX
    Explanations

    displacement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Displacement
    -0.76
    Displacement
    -0.75
    displacement
    -0.70
     prochaines
    -0.67
     displacement
    -0.65
     Theſe
    -0.64
     Beſ
    -0.61
     vermelhas
    -0.60
     betweenstory
    -0.59
    ItemBackground
    -0.58
    POSITIVE LOGITS
    volving
    0.59
    :✨
    0.57
    ing
    0.56
    NameInMap
    0.55
     a
    0.50
    ary
    0.50
     an
    0.50
     against
    0.49
     loans
    0.49
    Literatura
    0.48
    Act Density 0.011%

    No Known Activations