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

    Neuronpedia

    INDEX
    Explanations

    function parameters and types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    celona
    -1.32
    gnancy
    -1.31
        
    -1.30
    immen
    -1.23
    moil
    -1.21
    𝗰
    -1.19
    おわりに
    -1.18
    çadas
    -1.16
     邸
    -1.16
    hamburg
    -1.16
    POSITIVE LOGITS
     (
    1.33
    v
    1.26
     vogliono
    1.18
    man
    1.16
    ve
    1.12
    ですが
    1.08
    ‌.
    1.08
     at
    1.07
    .:
    1.05
    ing
    1.05
    Act Density 0.004%

    No Known Activations