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

    Neuronpedia

    INDEX
    Explanations

    numerical arrays and code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Cam
    -0.07
    Rare
    -0.07
    -F
    -0.07
    �
    -0.07
    >P
    -0.06
    鲽
    -0.06
    regions
    -0.06
     cou
    -0.06
    戈
    -0.06
    midt
    -0.06
    POSITIVE LOGITS
     BRE
    0.08
     accents
    0.08
    共产
    0.07
    会产生
    0.07
    你們
    0.07
    _INTR
    0.07
    UniformLocation
    0.07
    ::__
    0.07
     организм
    0.07
    拉着
    0.07
    Act Density 0.010%

    No Known Activations