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

    Neuronpedia

    INDEX
    Explanations

    radiation effects

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    電影
    -0.07
    -chair
    -0.07
    	client
    -0.06
    مین
    -0.06
     fundraiser
    -0.06
    판
    -0.06
     Name
    -0.06
    -0.06
    Write
    -0.06
    probability
    -0.06
    POSITIVE LOGITS
     evangel
    0.07
    .ColumnStyles
    0.06
    .START
    0.06
    .bo
    0.06
     val
    0.06
     purchased
    0.06
    )}>↵
    0.06
    localStorage
    0.06
    /app
    0.06
     RTBU
    0.06
    Act Density 0.025%

    No Known Activations