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

    Neuronpedia

    INDEX
    Explanations

    words associated with car interiors

    oai_token-act-pair · gemini-2.0-flash

    seat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     seat
    -2.00
     seats
    -1.91
    seat
    -1.69
     Seat
    -1.67
     Seats
    -1.63
    Seat
    -1.58
    seats
    -1.52
     chair
    -1.52
    Seats
    -1.40
     chairs
    -1.34
    POSITIVE LOGITS
    Vidite
    0.60
     becauſe
    0.58
    SBATCH
    0.56
    Chham
    0.55
     myſelf
    0.54
    omeness
    0.54
     itſelf
    0.53
    DebuggerNonUser
    0.53
    uterie
    0.52
    Odkazy
    0.52
    Act Density 9.308%

    No Known Activations