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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     incorporar
    -0.08
    zenten
    -0.08
     aanbevel
    -0.07
    -friendly
    -0.07
    Angles
    -0.07
    建议
    -0.07
     öner
    -0.07
    ്സ
    -0.07
    Friendly
    -0.07
    uml
    -0.07
    POSITIVE LOGITS
     resilience
    0.11
     Fähigkeiten
    0.09
     vaardigheden
    0.09
     capacités
    0.09
     perseverance
    0.09
     ક્ષ
    0.09
     exhilar
    0.09
     courage
    0.09
     വള
    0.09
     desconhe
    0.09
    Act Density 0.028%

    No Known Activations