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

    Neuronpedia

    INDEX
    Explanations

    type

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kurdish
    -0.06
     DIG
    -0.06
    Psi
    -0.06
     الدولة
    -0.06
    BU
    -0.06
     nb
    -0.06
    _nb
    -0.06
    _TREE
    -0.06
    oints
    -0.06
    Kenn
    -0.06
    POSITIVE LOGITS
    .sell
    0.07
    くだ
    0.06
     vampire
    0.06
    :none
    0.06
    alli
    0.06
    aptop
    0.06
    -sdk
    0.06
     foyer
    0.06
     stamp
    0.06
    USTOM
    0.06
    Act Density 0.000%

    No Known Activations