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

    Neuronpedia

    INDEX
    Explanations

    |

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bağlı
    -0.08
    ian
    -0.08
    ς
    -0.07
    eliac
    -0.07
    eshire
    -0.07
    ลม
    -0.07
     admire
    -0.07
    .JsonIgnore
    -0.07
    ：“
    -0.07
    heard
    -0.07
    POSITIVE LOGITS
     significantly
    0.08
     DEV
    0.07
    有利于
    0.07
    _home
    0.07
     Freddy
    0.07
     durable
    0.07
    -private
    0.07
    _AUTH
    0.07
    resolver
    0.07
    说我
    0.07
    Act Density 0.002%

    No Known Activations