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

    Neuronpedia

    INDEX
    Explanations

    if

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    titles
    -0.08
    ulant
    -0.07
     concise
    -0.07
     Charleston
    -0.06
    'Re
    -0.06
    foreign
    -0.06
    	Dictionary
    -0.06
     Se
    -0.06
     포함
    -0.06
    앤
    -0.06
    POSITIVE LOGITS
    .tool
    0.07
    .HOUR
    0.06
     жов
    0.06
     convent
    0.06
    이가
    0.06
     amino
    0.06
     base
    0.06
     Lily
    0.06
    .float
    0.06
     Greenland
    0.06
    Act Density 0.035%

    No Known Activations