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

    Neuronpedia

    INDEX
    Explanations

    Q

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    삽
    -0.08
     treadmill
    -0.07
    _RF
    -0.07
     Mountains
    -0.07
    _spacing
    -0.07
    ZZ
    -0.07
    -cigaret
    -0.07
     patrols
    -0.07
    وخ
    -0.07
     explosive
    -0.07
    POSITIVE LOGITS
    ┞
    0.07
    α
    0.07
    🅽
    0.07
    Q
    0.07
    _query
    0.07
    ,a
    0.07
    便可
    0.07
    🦃
    0.07
     Caroline
    0.07
    ㍉
    0.06
    Act Density 0.004%

    No Known Activations