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

    Neuronpedia

    INDEX
    Explanations

    equation definitions and calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     размещ
    -0.08
     établissements
    -0.07
    остав
    -0.07
     remarks
    -0.07
     kindlasti
    -0.07
    -facing
    -0.07
    .Match
    -0.07
    -managed
    -0.07
     regrets
    -0.07
    ász
    -0.07
    POSITIVE LOGITS
     customised
    0.09
     invented
    0.09
     strangely
    0.09
     weird
    0.09
    şk
    0.09
     kuw
    0.09
    人为
    0.09
     kå
    0.08
    创造
    0.08
     biro
    0.08
    Act Density 0.020%

    No Known Activations