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

    Neuronpedia

    INDEX
    Explanations

    List formatting characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.08
    kul
    -0.07
    BSD
    -0.07
    ensitivity
    -0.07
    мат
    -0.07
     Horizons
    -0.07
    /examples
    -0.07
     Micros
    -0.07
    atering
    -0.07
     possibility
    -0.07
    POSITIVE LOGITS
    准备
    0.12
     준비
    0.11
    Preparation
    0.10
    .Initialize
    0.10
     préparer
    0.10
    準
    0.10
     먼저
    0.10
     तयारी
    0.10
     groundwork
    0.10
     Preparation
    0.10
    Act Density 0.044%

    No Known Activations