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

    Neuronpedia

    INDEX
    Explanations

    and or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    INVALID
    -0.07
    lando
    -0.07
     gear
    -0.06
     librarian
    -0.06
    ToFront
    -0.06
    zza
    -0.06
     even
    -0.06
     ти
    -0.06
    แฟ
    -0.06
    isz
    -0.06
    POSITIVE LOGITS
    legates
    0.07
    hyth
    0.06
     Deadline
    0.06
     extradition
    0.06
    imetype
    0.06
    0.06
    0.06
     newbie
    0.06
     سلامت
    0.06
    byter
    0.06
    Act Density 0.214%

    No Known Activations