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

    Neuronpedia

    INDEX
    Explanations

    dear

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mitch
    -0.07
     слово
    -0.07
    Nothing
    -0.07
    }")
    -0.07
     два
    -0.07
     Kostenlos
    -0.06
     clinically
    -0.06
     Health
    -0.06
    											↵
    -0.06
     technically
    -0.06
    POSITIVE LOGITS
     dear
    0.10
    Dear
    0.09
     Dear
    0.09
     quer
    0.07
    ears
    0.07
    -Mail
    0.07
    Pear
    0.06
    rial
    0.06
    <dim
    0.06
     Pear
    0.06
    Act Density 0.008%

    No Known Activations