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

    Neuronpedia

    INDEX
    Explanations

    war

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     coke
    -0.07
     Confeder
    -0.07
     примерно
    -0.06
    税
    -0.06
     protects
    -0.06
    EP
    -0.06
    .slot
    -0.06
     Taxes
    -0.06
     Surprise
    -0.06
     برخ
    -0.06
    POSITIVE LOGITS
    roids
    0.07
    ≦
    0.06
    anzeigen
    0.06
     assms
    0.06
     "&
    0.06
    ighted
    0.06
    ندگان
    0.06
     recursive
    0.06
    chosen
    0.06
     meu
    0.06
    Act Density 0.036%

    No Known Activations