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

    Neuronpedia

    INDEX
    Explanations

    G

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    视线
    -0.08
    形态
    -0.07
    spotify
    -0.07
    YPE
    -0.07
    ElapsedTime
    -0.07
    勘
    -0.07
    Jos
    -0.06
    -pass
    -0.06
    xmin
    -0.06
     Cannot
    -0.06
    POSITIVE LOGITS
    タン
    0.07
    _sibling
    0.07
    🦅
    0.07
     _
    0.07
     goods
    0.07
    相应的
    0.06
     fireworks
    0.06
    stras
    0.06
     jButton
    0.06
     processors
    0.06
    Act Density 0.000%

    No Known Activations