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

    Neuronpedia

    INDEX
    Explanations

    code explanations and examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wife
    0.37
     Honorary
    0.37
     Lovers
    0.35
     Owner
    0.35
     Silhouette
    0.34
     Spouse
    0.34
     celebrating
    0.33
     Owners
    0.32
     Drafting
    0.32
     धमाकेदार
    0.32
    POSITIVE LOGITS
    GUID
    0.38
    Christian
    0.38
    原則
    0.36
    Ideally
    0.35
    simplified
    0.34
     simplifies
    0.34
    Итак
    0.33
    原则
    0.33
    oxid
    0.32
    失
    0.32
    Act Density 0.127%

    No Known Activations