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

    Neuronpedia

    INDEX
    Explanations

    loaders and spinners

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aslında
    -0.09
    .doc
    -0.07
     �
    -0.06
    ?p
    -0.06
     souvenir
    -0.06
    _notification
    -0.06
    _office
    -0.06
     attn
    -0.06
     borderline
    -0.06
    poň
    -0.06
    POSITIVE LOGITS
    송
    0.07
     Crunch
    0.07
    _make
    0.06
    님이
    0.06
     efficiencies
    0.06
    /Header
    0.06
     misses
    0.06
    Sensor
    0.06
     yiy
    0.06
     Fence
    0.06
    Act Density 0.011%

    No Known Activations