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

    Neuronpedia

    INDEX
    Explanations

    months

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .rule
    -0.07
     =>↵
    -0.07
    ultiply
    -0.07
    县委
    -0.07
     who
    -0.07
     vision
    -0.07
     str
    -0.07
     bind
    -0.07
    _WE
    -0.07
     improve
    -0.06
    POSITIVE LOGITS
    ơ
    0.08
    pełni
    0.07
    �
    0.07
     größ
    0.07
    疆
    0.07
    istles
    0.07
    Ε
    0.06
    疐
    0.06
     postId
    0.06
    Material
    0.06
    Act Density 0.004%

    No Known Activations