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

    Neuronpedia

    INDEX
    Explanations

    and S or **S**

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }
    0.35
    有着
    0.33
    IFS
    0.33
    ranging
    0.33
     focuses
    0.33
    程序员
    0.33
     signalled
    0.33
     manages
    0.33
     বহুম
    0.32
     hub
    0.32
    POSITIVE LOGITS
    嶠
    0.40
     задания
    0.39
    exercice
    0.38
     কিছুদিন
    0.37
     দেশটি
    0.37
     Sulfur
    0.37
     अकेला
    0.37
    谿
    0.37
    võ
    0.36
     لأن
    0.36
    Act Density 0.000%

    No Known Activations