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

    Neuronpedia

    INDEX
    Explanations

    personal stories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     enlarged
    -0.07
     Marion
    -0.07
    ết
    -0.07
    _original
    -0.06
     rempl
    -0.06
    Frank
    -0.06
    .front
    -0.06
    StartTime
    -0.06
    URED
    -0.06
     saver
    -0.06
    POSITIVE LOGITS
    "
↵
↵
↵
    0.07
     Apr
    0.07
     INITIAL
    0.07
    esc
    0.07
    Apr
    0.06
     stagn
    0.06
    axes
    0.06
    ">'+
    0.06
     combineReducers
    0.06
    ,},↵
    0.06
    Act Density 0.053%

    No Known Activations