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

    Neuronpedia

    INDEX
    Explanations

    Non-English language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     '}↵
    -0.08
    DER
    -0.08
     endure
    -0.07
     "}↵
    -0.07
     engr
    -0.07
     reciproc
    -0.07
    Pg
    -0.07
     ')
↵
    -0.07
     vegetal
    -0.07
    敬
    -0.07
    POSITIVE LOGITS
    াইজ
    0.10
     iba
    0.08
    ാറ്റ
    0.08
    ировании
    0.08
    િટ
    0.08
    沃
    0.08
     podr
    0.08
    olos
    0.08
    ସ
    0.08
    萨
    0.08
    Act Density 0.254%

    No Known Activations