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

    Neuronpedia

    INDEX
    Explanations

    ships

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ship
    -1.04
     Ship
    -0.94
    ship
    -0.79
    Ship
    -0.79
     SHIP
    -0.68
    EditorBrowsable
    -0.68
     ships
    -0.62
    SHIP
    -0.60
     Ships
    -0.57
     kor
    -0.57
    POSITIVE LOGITS
    seats
    0.55
    EndInit
    0.52
     antaranya
    0.51
    sets
    0.49
    wreck
    0.49
    cyc
    0.49
    stacks
    0.48
    mates
    0.48
     seats
    0.48
    layers
    0.48
    Act Density 0.028%

    No Known Activations