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

    Neuronpedia

    INDEX
    Explanations

    departure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -cloud
    -0.07
     rud
    -0.07
    -used
    -0.07
    .null
    -0.07
     matrices
    -0.07
     Knee
    -0.07
     jelly
    -0.06
     intertwined
    -0.06
     kne
    -0.06
     Functions
    -0.06
    POSITIVE LOGITS
     departed
    0.14
     departure
    0.13
     departing
    0.12
     depart
    0.11
    departure
    0.11
     Depart
    0.11
     départ
    0.10
    Depart
    0.09
    depart
    0.08
     dep
    0.08
    Act Density 0.005%

    No Known Activations