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

    Neuronpedia

    INDEX
    Explanations

    Technical details

    np_max-act-logits · gemini-2.0-flashTriggered by @majianfei030706
    New Auto-Interp
    Negative Logits
    jar
    -0.08
    �
    -0.07
    -decoration
    -0.07
    Buffer
    -0.07
     IList
    -0.07
    śmy
    -0.07
    péri
    -0.06
    Ce
    -0.06
    ø
    -0.06
    ät
    -0.06
    POSITIVE LOGITS
     enthus
    0.09
    可谓
    0.08
     launched
    0.07
    /version
    0.07
    戽
    0.07
    滏
    0.07
    斛
    0.07
    咩
    0.07
    愈加
    0.07
    早日
    0.07
    Act Density 0.043%

    No Known Activations