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

    Neuronpedia

    INDEX
    Explanations

    hygiene and body part discussion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dù
    0.47
     orphanage
    0.42
     মর্টার
    0.41
     dynamite
    0.39
     いつ
    0.39
     êtres
    0.39
    佰
    0.38
     memset
    0.38
    能量
    0.37
     guerras
    0.37
    POSITIVE LOGITS
    Next
    0.43
     Next
    0.40
    NEXT
    0.38
    XIII
    0.37
    เชิง
    0.37
    And
    0.37
    Avro
    0.37
     reflector
    0.36
    Autom
    0.36
    But
    0.36
    Act Density 0.000%

    No Known Activations