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

    Neuronpedia

    INDEX
    Explanations

    functional units

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sw
    -0.07
     Nordic
    -0.06
    _date
    -0.06
    周
    -0.06
     boasts
    -0.06
    (=
    -0.06
     induced
    -0.06
    ition
    -0.06
    (short
    -0.06
    .created
    -0.06
    POSITIVE LOGITS
    .fire
    0.07
    锦
    0.07
    icken
    0.07
     kullan
    0.06
    .TestTools
    0.06
    Wunused
    0.06
     mortar
    0.06
     aloud
    0.06
    card
    0.06
    HomeAsUpEnabled
    0.06
    Act Density 0.040%

    No Known Activations