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

    Neuronpedia

    INDEX
    Explanations

    will

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    inned
    -0.07
    ologist
    -0.07
     JL
    -0.07
    izioni
    -0.06
    VI
    -0.06
    Hash
    -0.06
    ology
    -0.06
     ruin
    -0.06
    ()}}↵
    -0.06
     Rifle
    -0.06
    POSITIVE LOGITS
    čení
    0.06
    .nome
    0.06
     Ever
    0.06
     офици
    0.06
     Dodgers
    0.06
    ificaciones
    0.06
     "-
    0.06
    McC
    0.06
     peux
    0.06
    (stmt
    0.06
    Act Density 0.477%

    No Known Activations