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

    Neuronpedia

    INDEX
    Explanations

    accused

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     variation
    -0.07
     Fuller
    -0.07
     Portions
    -0.07
     rl
    -0.07
    ▏▏
    -0.06
    926
    -0.06
     Sheldon
    -0.06
     receptive
    -0.06
    网络
    -0.06
     Renaissance
    -0.06
    POSITIVE LOGITS
     accusation
    0.09
     accused
    0.09
     accusations
    0.09
     accuses
    0.08
     Acc
    0.08
     accus
    0.08
    zeich
    0.07
     accusing
    0.07
     Claim
    0.07
     "[
    0.07
    Act Density 0.008%

    No Known Activations