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

    Neuronpedia

    INDEX
    Explanations

    replacement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     replacement
    -2.69
    replacement
    -2.50
     replacements
    -2.42
     Replacement
    -2.39
     replace
    -2.36
     replacing
    -2.36
     replaced
    -2.31
    Replacement
    -2.27
     substitution
    -2.25
     substitute
    -2.22
    POSITIVE LOGITS
    帖最后由
    0.50
    mybatisplus
    0.47
    UrlResolution
    0.45
    Personendaten
    0.43
     parts
    0.43
     ý
    0.43
     potential
    0.42
     hundred
    0.42
     sar
    0.42
    ietal
    0.42
    Act Density 0.243%

    No Known Activations