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

    Neuronpedia

    INDEX
    Explanations

    accident

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Row
    -0.07
     Hub
    -0.07
     พระ
    -0.07
    levance
    -0.07
     Qin
    -0.07
     Tow
    -0.07
    .groups
    -0.07
     Hose
    -0.06
     Thu
    -0.06
     Place
    -0.06
    POSITIVE LOGITS
     accident
    0.16
     accidents
    0.13
     Accident
    0.10
     accidentally
    0.09
     accidental
    0.08
     disabilities
    0.07
    acier
    0.07
     pretty
    0.07
    adder
    0.07
     wreck
    0.07
    Act Density 0.008%

    No Known Activations