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

    Neuronpedia

    INDEX
    Explanations

    Phone case accessibility

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .props
    -0.07
    ấp
    -0.07
     puls
    -0.07
     wi
    -0.07
    (trigger
    -0.07
     Tiếp
    -0.07
     nug
    -0.06
    -calendar
    -0.06
    polation
    -0.06
    _character
    -0.06
    POSITIVE LOGITS
    破损
    0.08
    别
    0.07
    被
    0.07
    _code
    0.07
     slid
    0.07
    `↵
    0.07
    .NewLine
    0.07
    	f
    0.07
    due
    0.07
    ⼊
    0.07
    Act Density 0.076%

    No Known Activations