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

    Neuronpedia

    INDEX
    Explanations

    situations, events, phenomena

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -to
    -0.08
     importing
    -0.07
    ---
    -0.07
    ıs
    -0.06
     Peace
    -0.06
     Arab
    -0.06
    ALAR
    -0.06
    aising
    -0.06
     elk
    -0.06
    Fully
    -0.06
    POSITIVE LOGITS
    Sci
    0.07
     مقدم
    0.06
    벤
    0.06
     foll
    0.06
     urged
    0.06
    proc
    0.06
     Sci
    0.06
    _ISO
    0.06
    direction
    0.06
    Sc
    0.06
    Act Density 0.430%

    No Known Activations