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

    Neuronpedia

    INDEX
    Explanations

    spaced

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    kelig
    -0.07
    @",
    -0.07
     mary
    -0.07
    -properties
    -0.06
     teens
    -0.06
    こんな
    -0.06
     inflicted
    -0.06
    _CONTROLLER
    -0.06
    rounded
    -0.06
    nv
    -0.06
    POSITIVE LOGITS
    607
    0.07
    006
    0.06
    є
    0.06
    นค
    0.06
    003
    0.06
    ĩnh
    0.06
    言わ
    0.06
    풍
    0.06
     подк
    0.06
    立刻
    0.06
    Act Density 0.012%

    No Known Activations