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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    toa
    -0.07
     赤
    -0.07
    vr
    -0.07
    arım
    -0.07
     Cow
    -0.07
    ain
    -0.06
     kennen
    -0.06
     itch
    -0.06
    杰
    -0.06
    vp
    -0.06
    POSITIVE LOGITS
    ultureInfo
    0.06
     bureaucracy
    0.06
    _tools
    0.06
     sacrifice
    0.06
    `.
    0.06
    allocate
    0.06
    _mat
    0.06
    _LINK
    0.06
    Beauty
    0.06
    .pet
    0.06
    Act Density 0.006%

    No Known Activations