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

    Neuronpedia

    INDEX
    Explanations

    grammatical constructs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     leicht
    -0.07
     OFFSET
    -0.07
    (Post
    -0.07
    }${
    -0.07
    混合
    -0.07
    &apos
    -0.06
     blobs
    -0.06
     ober
    -0.06
    -mon
    -0.06
    وین
    -0.06
    POSITIVE LOGITS
    ENARIO
    0.07
    ież
    0.07
    Attendance
    0.06
    (define
    0.06
     maintained
    0.06
    ảm
    0.06
    _selected
    0.06
    ード
    0.06
    _weights
    0.06
     regard
    0.06
    Act Density 0.296%

    No Known Activations