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

    Neuronpedia

    INDEX
    Explanations

    dating

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reserves
    -0.08
     turbine
    -0.07
     storms
    -0.07
     welfare
    -0.07
     Bus
    -0.07
     edge
    -0.06
     words
    -0.06
     boats
    -0.06
     robin
    -0.06
     reservations
    -0.06
    POSITIVE LOGITS
     dating
    0.08
     Dating
    0.07
    /autoload
    0.06
     đàn
    0.06
    Î
    0.06
    ‌ان
    0.06
    (COLOR
    0.06
    ⌒
    0.06
    (sz
    0.06
    dating
    0.06
    Act Density 0.005%

    No Known Activations