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

    Neuronpedia

    INDEX
    Explanations

    words related to medical issues, viruses or hospital acquired infections

    oai_token-act-pair · gemini-2.0-flash

    negative events

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     accident
    -0.80
    RenderAtEndOf
    -0.71
     gap
    -0.70
    Accident
    -0.70
    accident
    -0.70
     acidente
    -0.66
     Incident
    -0.66
     incident
    -0.66
     ACCIDENT
    -0.65
     Accident
    -0.64
    POSITIVE LOGITS
     utafitiHapana
    0.74
     block
    0.74
    ρευ
    0.60
     JpaRepository
    0.59
    #+#
    0.55
     blow
    0.53
    mers
    0.53
     touch
    0.51
    واده
    0.51
    IntoConstraints
    0.50
    Act Density 4.701%

    No Known Activations