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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     MPL
    -0.06
     abstract
    -0.06
    PIP
    -0.06
     Chair
    -0.06
    inally
    -0.06
    otal
    -0.06
     آمد
    -0.06
    .previous
    -0.06
    [],
    -0.06
    忘
    -0.05
    POSITIVE LOGITS
    _projects
    0.07
    .ejb
    0.07
    _Model
    0.07
     Stmt
    0.07
    监听
    0.07
    ?>↵↵
    0.06
    剑
    0.06
    rases
    0.06
    дии
    0.06
     yardım
    0.06
    Act Density 0.009%

    No Known Activations