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

    Neuronpedia

    INDEX
    Explanations

    business/policy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Numerous
    -0.08
     birçok
    -0.08
     accesorios
    -0.07
    many
    -0.07
    LER
    -0.07
    pect
    -0.07
    许
    -0.07
     различные
    -0.07
     lax
    -0.07
    dik
    -0.07
    POSITIVE LOGITS
     মোক
    0.10
    roffenen
    0.09
    改善
    0.09
     Umoja
    0.08
    embre
    0.08
     melhorar
    0.08
    аъ
    0.08
     someday
    0.08
     stabil
    0.08
     overcoming
    0.08
    Act Density 0.208%

    No Known Activations