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

    Neuronpedia

    INDEX
    Explanations

    process

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    äche
    -0.08
     NAME
    -0.07
     MOD
    -0.07
    ías
    -0.07
     Egypt
    -0.07
    Word
    -0.06
    킬
    -0.06
    Though
    -0.06
    uesto
    -0.06
    st
    -0.06
    POSITIVE LOGITS
     صنعتی
    0.07
     Pradesh
    0.06
    amsung
    0.06
     Rudy
    0.06
    ..."
    0.06
     Disc
    0.06
    聊
    0.06
    marketing
    0.06
    orical
    0.06
     clandest
    0.06
    Act Density 0.066%

    No Known Activations