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

    Neuronpedia

    INDEX
    Explanations

    sequence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Capitol
    -0.07
    My
    -0.07
    /background
    -0.07
    Radius
    -0.07
    话
    -0.06
    _clr
    -0.06
    /q
    -0.06
    	TR
    -0.06
     symlink
    -0.06
    Pipeline
    -0.06
    POSITIVE LOGITS
    сяг
    0.06
    usting
    0.06
     beloved
    0.06
    níků
    0.06
    orges
    0.06
    "class
    0.06
    ihat
    0.06
     importantly
    0.06
     JSGlobal
    0.06
     beings
    0.06
    Act Density 0.038%

    No Known Activations