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

    Neuronpedia

    INDEX
    Explanations

    Beautiful things

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Offset
    -0.07
     Competition
    -0.07
     Shortly
    -0.07
    油画
    -0.07
    Capt
    -0.07
    exe
    -0.07
     Certificate
    -0.07
     chart
    -0.07
    irteen
    -0.06
    address
    -0.06
    POSITIVE LOGITS
    irá
    0.08
    getRoot
    0.07
    	Use
    0.07
    iais
    0.07
    化学品
    0.07
    骨干
    0.07
    _From
    0.07
    >Email
    0.06
    _handling
    0.06
    岿
    0.06
    Act Density 0.076%

    No Known Activations