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

    Neuronpedia

    INDEX
    Explanations

    two pump hearts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kont
    0.42
     भंड
    0.39
    高级
    0.39
     обла
    0.38
     ऑर्
    0.37
     sixteenth
    0.37
     marginBottom
    0.36
     disf
    0.36
    XVI
    0.36
    最重要的
    0.36
    POSITIVE LOGITS
    ueger
    0.37
     allergens
    0.37
     traffic
    0.36
    ocial
    0.34
     indirect
    0.34
     &
    0.34
     enforced
    0.33
    まって
    0.33
     innocent
    0.33
     indirectly
    0.33
    Act Density 0.003%

    No Known Activations