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

    Neuronpedia

    INDEX
    Explanations

    same

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    FINITY
    -0.07
     setContentView
    -0.07
    SetTitle
    -0.07
     OMIT
    -0.07
    .staff
    -0.06
    (iv
    -0.06
    481
    -0.06
    -0.06
    .rep
    -0.06
    世
    -0.06
    POSITIVE LOGITS
    /front
    0.07
     發
    0.06
    asje
    0.06
    ινε
    0.06
     Anything
    0.06
    НО
    0.06
     acknowledges
    0.06
    지원
    0.06
     clo
    0.06
    :int
    0.06
    Act Density 0.006%

    No Known Activations