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

    Neuronpedia

    INDEX
    Explanations

    subpackage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     날
    -0.06
    ぅ
    -0.06
    奏
    -0.06
    َب
    -0.06
     programmers
    -0.06
     했다
    -0.06
     суспіль
    -0.06
    Foo
    -0.06
    __(*
    -0.06
    )、
    -0.06
    POSITIVE LOGITS
    PLACE
    0.07
     suburb
    0.07
    _mu
    0.07
    UNDER
    0.07
     Laptop
    0.06
    DBC
    0.06
     PCM
    0.06
    Guard
    0.06
    orry
    0.06
    Mech
    0.06
    Act Density 0.000%

    No Known Activations