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

    Neuronpedia

    INDEX
    Explanations

    places

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Comedy
    -0.07
    _SCHEMA
    -0.07
     Cement
    -0.07
    𝗰
    -0.07
    �
    -0.07
    _disabled
    -0.07
    .*/↵
    -0.06
    _folder
    -0.06
    伸手
    -0.06
    _rt
    -0.06
    POSITIVE LOGITS
    抽象
    0.07
     extend
    0.07
     Spring
    0.07
     своего
    0.07
    Patch
    0.07
    ersions
    0.06
    Renderer
    0.06
     flatt
    0.06
    イト
    0.06
     Prescott
    0.06
    Act Density 0.008%

    No Known Activations